© 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 EvalsExportsinterp-engineNEWAPI 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. 2120
    Prev
    Next
    INDEX
    Explanations

    traffic-related terms and regulations

    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
    288
    +0.14
    0.8%
    515
    +0.11
    0.6%
    277
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.07
    289
    +0.11
    0.02
    325
    +0.08
    0.04
    Negative Logits
    monds
    -0.62
    kai
    -0.60
    yo
    -0.60
    estamp
    -0.59
    ãģ¦
    -0.59
    ership
    -0.59
    marine
    -0.57
    itude
    -0.57
    unta
    -0.57
     tofu
    -0.57
    POSITIVE LOGITS
    icular
    0.81
    riages
    0.64
     accident
    0.57
    ILLE
    0.55
     Nost
    0.54
     Gree
    0.53
     Expend
    0.53
    itas
    0.53
     Gork
    0.53
    igating
    0.52
    Activations Density 0.476%

    No Known Activations