© 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. 5533
    Prev
    Next
    INDEX
    Explanations

    mentions of names of cities or locations

    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
    521
    +0.13
    0.5%
    667
    +0.10
    0.4%
    402
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.13
    0.06
    404
    +0.10
    0.05
    530
    +0.10
    0.04
    Negative Logits
    vertisements
    -0.85
    gins
    -0.81
    row
    -0.76
    Reviewer
    -0.76
    orters
    -0.75
    istration
    -0.74
    thood
    -0.74
    road
    -0.73
    intern
    -0.73
    angers
    -0.73
    POSITIVE LOGITS
    £ı
    0.88
     Leban
    0.85
    ION
    0.85
     EDITION
    0.85
    IDER
    0.83
     Lumpur
    0.83
     THR
    0.83
    ABLE
    0.81
    PRESS
    0.81
     BRA
    0.81
    Activations Density 0.430%

    No Known Activations