Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8366
    Prev
    Next
    INDEX
    Explanations

    phrases related to rock and roll music

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the conjunction "and" and related phrases in the context of rock and roll

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fen
    -0.67
    advertisement
    -0.66
    ISA
    -0.66
    ihar
    -0.64
     <[
    -0.64
    GROUP
    -0.62
    assian
    -0.62
     JPM
    -0.61
    auna
    -0.61
    taboola
    -0.60
    POSITIVE LOGITS
     roll
    1.10
     Roll
    1.04
    roll
    1.04
    rollers
    0.97
     roller
    0.95
     Roses
    0.94
    Roll
    0.92
    roller
    0.88
     Chips
    0.87
    rolling
    0.83
    Activations Density 0.099%

    No Known Activations