© 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. 13674
    Prev
    Next
    INDEX
    Explanations

    text inspired by various sources or 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
    +0.32
    1.7%
    647
    +0.12
    0.6%
    362
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.32
    0.36
    608
    +0.12
    0.29
    362
    +0.11
    0.21
    Negative Logits
    asive
    -0.71
    arant
    -0.67
    til
    -0.66
    sided
    -0.64
    due
    -0.63
    insured
    -0.63
    acity
    -0.62
    oided
    -0.61
    ainer
    -0.61
    fixed
    -0.61
    POSITIVE LOGITS
     classic
    0.74
     motif
    0.65
     Pam
    0.65
     classics
    0.65
     inspiration
    0.65
     tropes
    0.65
     sentiments
    0.65
     imagery
    0.63
     recol
    0.63
     footsteps
    0.62
    Activations Density 14.738%

    No Known Activations