© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40822
    Prev
    Next
    INDEX
    Explanations

    locations or destinations

    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%
    393
    +0.19
    0.9%
    608
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.37
    608
    +0.19
    0.30
    640
    +0.14
    0.33
    Negative Logits
     held
    -0.70
    shown
    -0.69
    wine
    -0.66
    rap
    -0.66
     risked
    -0.65
    IRC
    -0.63
    pret
    -0.63
    few
    -0.62
    ²¾
    -0.62
     Factors
    -0.62
    POSITIVE LOGITS
     enlightenment
    0.80
     fruition
    0.76
    atown
    0.74
     academia
    0.71
    aterasu
    0.70
     perfection
    0.70
     finish
    0.70
     salvation
    0.68
    dinand
    0.68
     anonymity
    0.67
    Activations Density 15.390%

    No Known Activations