© 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. 34408
    Prev
    Next
    INDEX
    Explanations

    patterns related to numbers, measurements, and technical specifications

    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
    239
    +0.10
    0.6%
    104
    +0.09
    0.5%
    302
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.30
    6
    +0.09
    0.20
    107
    +0.09
    0.07
    Negative Logits
    schild
    -0.76
    ouver
    -0.70
    enhagen
    -0.69
    allery
    -0.60
    organ
    -0.57
    yson
    -0.56
    mouse
    -0.55
    abwe
    -0.55
    stad
    -0.55
    usercontent
    -0.55
    POSITIVE LOGITS
     GHz
    0.57
     Centauri
    0.54
    thood
    0.53
     Venom
    0.52
     Siren
    0.52
    nikov
    0.51
    uous
    0.51
    GHz
    0.50
     Viper
    0.50
    ALSE
    0.50
    Activations Density 14.968%

    No Known Activations