© 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. 5578
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting records or achieving goals

    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
    640
    +0.15
    0.5%
    636
    +0.14
    0.5%
    560
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.15
    0.07
    37
    +0.14
    0.04
    397
    +0.14
    0.04
    Negative Logits
    steen
    -0.91
    issance
    -0.87
     Macedonia
    -0.87
    cription
    -0.87
    itely
    -0.84
     cull
    -0.84
    uman
    -0.84
    asketball
    -0.84
    hent
    -0.83
     reprint
    -0.83
    POSITIVE LOGITS
    eer
    1.12
    tle
    1.09
    ilts
    1.02
     aside
    1.01
     abl
    0.99
    pring
    0.96
     apart
    0.95
     precedence
    0.95
     groundwork
    0.94
    flame
    0.93
    Activations Density 0.746%

    No Known Activations