© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    words related to media production, such as movies, actors, interviews, and characters

    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
    +0.27
    1.3%
    508
    +0.10
    0.5%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.39
    640
    +0.10
    0.34
    362
    +0.10
    0.19
    Negative Logits
    ¯¯¯¯¯¯¯¯
    -0.85
    ¯¯
    -0.69
    sis
    -0.68
    ¯¯¯¯
    -0.66
    sett
    -0.65
    heric
    -0.65
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.65
    ccording
    -0.63
    shell
    -0.63
    zers
    -0.62
    POSITIVE LOGITS
     mentioning
    0.86
     mentions
    0.81
     Kislyak
    0.75
    lihood
    0.73
     aloud
    0.73
     mention
    0.69
    enance
    0.63
     prominently
    0.61
    pages
    0.61
     incidentally
    0.59
    Activations Density 17.629%

    No Known Activations