© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1581
    Prev
    Next
    INDEX
    Explanations

    information related to adjusting and managing various aspects, such as vehicle balance, speed management, braking techniques, space management, and other adjustment-related topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    62
    +0.15
    0.5%
    288
    +0.15
    0.5%
    624
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.08
    195
    +0.15
    0.02
    507
    +0.14
    0.05
    Negative Logits
    OGR
    -0.87
    jay
    -0.87
    ################################
    -0.86
    CRIP
    -0.86
    Å
    -0.86
    chu
    -0.85
    ILE
    -0.84
    NetMessage
    -0.83
    emon
    -0.83
    fruit
    -0.82
    POSITIVE LOGITS
    ments
    1.27
     adjustment
    1.18
     adjustments
    1.13
     adjust
    1.03
    adjust
    0.94
     Adjust
    0.94
     adjusting
    0.93
     mund
    0.93
     knob
    0.92
    enhagen
    0.92
    Activations Density 1.033%

    No Known Activations