© 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. 13774
    Prev
    Next
    INDEX
    Explanations

    mentions of statistics or numerical data

    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
    +0.18
    1.0%
    393
    +0.11
    0.6%
    674
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.38
    745
    +0.11
    -0.14
    393
    +0.08
    0.33
    Negative Logits
     oath
    -0.58
    »Ĵ
    -0.55
    sett
    -0.54
    wcsstore
    -0.52
     ×
    -0.51
    ģ
    -0.49
    pin
    -0.49
     principals
    -0.48
    verning
    -0.48
    Planet
    -0.48
    POSITIVE LOGITS
    efficiency
    0.90
    ordinate
    0.70
    effic
    0.69
     tandem
    0.67
     popularity
    0.66
     incidence
    0.65
    ventory
    0.63
     increments
    0.62
    activity
    0.61
     volume
    0.61
    Activations Density 15.766%

    No Known Activations