© 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. 32936
    Prev
    Next
    INDEX
    Explanations

    mentions of loss or commemoration

    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
    631
    +0.13
    0.5%
    211
    +0.11
    0.5%
    598
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.13
    0.36
    480
    +0.11
    -0.13
    362
    +0.11
    0.11
    Negative Logits
    aughs
    -0.94
    hift
    -0.80
    peria
    -0.79
    ilion
    -0.78
    ndum
    -0.77
    imer
    -0.77
    olson
    -0.76
    forth
    -0.76
    gars
    -0.76
    heit
    -0.75
    POSITIVE LOGITS
    æ©
    0.89
     RTX
    0.88
     strawberries
    0.88
    ãģ®ç
    0.81
     Getty
    0.81
    ãģ®å
    0.78
     Schwarzenegger
    0.78
     Reuters
    0.77
    åij
    0.76
    independence
    0.75
    Activations Density 21.375%

    No Known Activations