© 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. 45736
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    447
    +0.21
    1.0%
    339
    +0.09
    0.5%
    349
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.22
    349
    +0.09
    0.05
    371
    +0.09
    0.08
    Negative Logits
    utive
    -0.86
    atories
    -0.75
    eas
    -0.72
    roach
    -0.72
    mble
    -0.71
    rator
    -0.71
    spring
    -0.70
    arial
    -0.69
    unda
    -0.68
    rators
    -0.68
    POSITIVE LOGITS
     Browne
    0.75
    sonian
    0.73
    acks
    0.69
    OGR
    0.65
    stown
    0.65
     Gunn
    0.64
    itton
    0.61
     Reuters
    0.59
     Yor
    0.58
    bilt
    0.58
    Activations Density 8.557%

    No Known Activations