Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5198
    Prev
    Next
    INDEX
    Explanations

    address locations and directions in a city or town

    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
    71
    +0.04
    0.4%
    761
    +0.04
    0.4%
    318
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.04
    0.04
    365
    +0.04
    0.03
    496
    +0.04
    0.03
    Negative Logits
    uary
    -0.41
     simul
    -0.31
    udo
    -0.31
    iaries
    -0.29
    oggles
    -0.29
     rub
    -0.29
    idon
    -0.29
    oggle
    -0.29
    hai
    -0.28
    GGGGGGGG
    -0.28
    POSITIVE LOGITS
    ãĥ¤
    0.33
    unknown
    0.30
    visory
    0.30
    capacity
    0.29
    large
    0.29
    LB
    0.29
    (_
    0.28
    personal
    0.28
     Thumbnails
    0.27
     Altern
    0.27
    Activations Density 0.056%

    No Known Activations