© 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
    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. 1214
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary preferences and restrictions

    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
    0.6%
    704
    +0.12
    0.6%
    490
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.23
    711
    +0.12
    0.07
    575
    +0.10
    0.14
    Negative Logits
    assies
    -0.85
    itars
    -0.74
    riages
    -0.70
    eworks
    -0.68
     Rooms
    -0.66
    doms
    -0.66
    rencies
    -0.66
    arenthood
    -0.66
    vironments
    -0.65
    ernels
    -0.65
    POSITIVE LOGITS
     standpoint
    0.94
     spokesperson
    0.78
    ussian
    0.77
     perspective
    0.77
     inhibitor
    0.73
     sized
    0.71
    statement
    0.71
    perate
    0.69
     spokeswoman
    0.69
    ounding
    0.68
    Activations Density 4.523%

    No Known Activations