© 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. 60
    Prev
    Next
    INDEX
    Explanations

    words related to interior or being inside of something

    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
    526
    +0.15
    0.5%
    59
    +0.14
    0.5%
    352
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.15
    0.04
    324
    +0.14
    0.04
    491
    +0.13
    0.03
    Negative Logits
    enegger
    -1.31
    eday
    -1.05
    enez
    -1.03
     Cly
    -1.02
    yah
    -1.02
    tle
    -1.01
    visor
    -0.99
    uyomi
    -0.98
    ministic
    -0.95
    lda
    -0.93
    POSITIVE LOGITS
    vert
    1.17
    doors
    0.99
     parentheses
    0.99
     latex
    0.94
     chambers
    0.91
    inqu
    0.89
     bedrooms
    0.87
     vivo
    0.87
    door
    0.86
     seams
    0.86
    Activations Density 0.861%

    No Known Activations