© 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. 35289
    Prev
    Next
    INDEX
    Explanations

    discussions and opinions related to sports teams and players

    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
    +0.20
    1.0%
    640
    +0.09
    0.4%
    88
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.35
    640
    +0.09
    0.32
    679
    +0.09
    0.28
    Negative Logits
    ascript
    -0.67
    reated
    -0.63
    è¦ļéĨĴ
    -0.62
    ome
    -0.62
    nai
    -0.60
    natureconservancy
    -0.60
    quartered
    -0.60
    à¨
    -0.59
    İĭ
    -0.58
    conservancy
    -0.57
    POSITIVE LOGITS
     bye
    0.81
    bye
    0.75
     Wrong
    0.70
     yeah
    0.68
     congratulations
    0.67
    yeah
    0.66
     maybe
    0.64
     Bye
    0.63
     yes
    0.62
     lets
    0.62
    Activations Density 15.980%

    No Known Activations