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

    Neuronpedia

    Jacobian LensNEW
    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. 12420
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical data related to physics or engineering

    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
    526
    +0.18
    0.7%
    624
    +0.14
    0.5%
    462
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.18
    0.04
    288
    +0.14
    0.07
    526
    +0.13
    0.01
    Negative Logits
    uments
    -0.85
    ificate
    -0.83
    uity
    -0.80
    ophile
    -0.79
     guilty
    -0.79
    onial
    -0.75
    tiny
    -0.74
    osphere
    -0.74
    ¯¯¯¯
    -0.72
    Cub
    -0.72
    POSITIVE LOGITS
    whelming
    1.27
    lay
    1.17
    flow
    1.13
    ride
    1.12
    haul
    1.03
    leaf
    1.02
    loaded
    1.00
    due
    1.00
    lap
    0.99
    stable
    0.97
    Activations Density 0.658%

    No Known Activations