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. 3058
    Prev
    Next
    INDEX
    Explanations

    fans or supporters of various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fandoms and fan-related content

    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
    of
    -0.63
    uci
    -0.61
     Seymour
    -0.59
     Vall
    -0.59
     Marlins
    -0.58
    å§«
    -0.58
     Bhar
    -0.58
     Brow
    -0.57
     Hos
    -0.56
     Kitt
    -0.56
    POSITIVE LOGITS
    paces
    0.74
    ioned
    0.73
    reciation
    0.72
    chool
    0.67
     prominently
    0.65
    âĨij
    0.65
    vertisements
    0.65
    oaded
    0.64
    azeera
    0.64
    abilia
    0.63
    Activations Density 0.564%

    No Known Activations