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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1225
    Prev
    Next
    INDEX
    Explanations

    phrases related to community events, local news, and announcements

    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
    393
    +0.16
    0.7%
    246
    +0.12
    0.6%
    362
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.16
    0.07
    159
    +0.12
    0.06
    45
    +0.12
    0.04
    Negative Logits
    theless
    -0.94
    culosis
    -0.79
     Nare
    -0.71
    ovember
    -0.71
    cade
    -0.70
    ason
    -0.69
    icipated
    -0.68
    regor
    -0.67
    emonium
    -0.67
    ython
    -0.67
    POSITIVE LOGITS
     clothes
    0.67
    selves
    0.62
     product
    0.62
     text
    0.61
     gir
    0.60
    ise
    0.60
     baggage
    0.59
    sle
    0.59
    sed
    0.58
     direction
    0.58
    Activations Density 1.521%

    No Known Activations