© 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 Local
    9. 6-RES_SCL-AJT
    11. 12913
    Prev
    Next
    INDEX
    Explanations

    information related to legal documents or court proceedings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    110
    +0.05
    0.4%
    264
    +0.04
    0.4%
    360
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.05
    -0.04
    308
    +0.04
    0.08
    731
    +0.04
    0.03
    Negative Logits
     rhy
    -0.37
    ews
    -0.35
     guiActiveUn
    -0.34
     interpol
    -0.34
     Logged
    -0.33
    beat
    -0.32
    vous
    -0.32
     outp
    -0.32
     pandemonium
    -0.32
    oaded
    -0.32
    POSITIVE LOGITS
     PLA
    0.38
     XL
    0.37
     Folder
    0.35
     Etsy
    0.35
    cheon
    0.34
     Gibraltar
    0.34
    cv
    0.34
     747
    0.33
     Delivery
    0.33
     Regist
    0.33
    Activations Density 17.955%

    No Known Activations