© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14643
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or formal documents and terms

    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
    +0.13
    0.5%
    146
    +0.12
    0.5%
    86
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.13
    0.03
    509
    +0.12
    0.03
    146
    +0.12
    0.03
    Negative Logits
     Ribbon
    -0.82
     Patriarch
    -0.81
     Trees
    -0.81
     corrid
    -0.78
    etts
    -0.75
     Beet
    -0.73
     swe
    -0.73
     bunk
    -0.72
    natureconservancy
    -0.71
     Tup
    -0.71
    POSITIVE LOGITS
    resy
    1.03
     purposes
    1.02
    ptions
    0.98
    rative
    0.95
    tesy
    0.93
    ajor
    0.92
    farious
    0.92
    veyard
    0.91
    afe
    0.90
    istry
    0.90
    Activations Density 0.404%

    No Known Activations