© 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 Local
    9. 6-RES_SCL-AJT
    11. 39987
    Prev
    Next
    INDEX
    Explanations

    tokens written in a different language, potentially with special characters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    207
    +0.14
    0.6%
    131
    +0.12
    0.5%
    325
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.34
    107
    +0.12
    0.05
    449
    +0.11
    0.10
    Negative Logits
    berman
    -0.83
    ndra
    -0.77
    nesday
    -0.76
    cake
    -0.73
    raints
    -0.72
    omorphic
    -0.70
     imaginable
    -0.70
    regor
    -0.68
    achus
    -0.68
     volunt
    -0.67
    POSITIVE LOGITS
    externalActionCode
    0.85
    cknow
    0.79
    #$
    0.76
     horm
    0.75
    cknowled
    0.72
    BSD
    0.69
    osterone
    0.69
     antioxid
    0.68
    resy
    0.67
     Lumpur
    0.66
    Activations Density 16.611%

    No Known Activations