© 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. 33168
    Prev
    Next
    INDEX
    Explanations

    references to specific video games and related terms

    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
    271
    +0.11
    0.6%
    360
    +0.11
    0.6%
    761
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.23
    326
    +0.11
    0.20
    709
    +0.08
    0.12
    Negative Logits
    govtrack
    -0.74
    ownt
    -0.68
    ustom
    -0.66
    otine
    -0.65
    stract
    -0.63
    river
    -0.62
    warts
    -0.62
    olin
    -0.60
    ombo
    -0.58
    astics
    -0.58
    POSITIVE LOGITS
     Andromeda
    0.81
    ilon
    0.69
     Ceres
    0.57
     Wolfe
    0.54
    ively
    0.54
    ledged
    0.52
    ives
    0.52
    uve
    0.52
    schild
    0.52
    pard
    0.52
    Activations Density 5.929%

    No Known Activations