© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 12273
    Prev
    Next
    INDEX
    Explanations

    instances of percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 99 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemImage
    -0.82
    stem
    -0.80
    holders
    -0.78
    holder
    -0.76
    rill
    -0.76
    board
    -0.71
    odynam
    -0.71
    âĹ¼
    -0.70
    loo
    -0.69
    handled
    -0.69
    POSITIVE LOGITS
    999
    1.24
    %:
    0.95
    LECT
    0.86
    ¢
    0.86
    %]
    0.84
    %-
    0.84
    %
    0.83
    090
    0.83
    %;
    0.82
    %,
    0.82
    Activations Density 0.017%

    No Known Activations