© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 2747
    Prev
    Next
    INDEX
    Explanations

    numerical values with percentage symbols and confidence intervals

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with statistical confidence levels and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.80
    sworth
    -0.72
    anian
    -0.68
    ItemImage
    -0.68
    holder
    -0.67
    boarding
    -0.66
    Demand
    -0.65
    untu
    -0.64
    board
    -0.64
    dress
    -0.63
    POSITIVE LOGITS
    %:
    1.04
    %-
    0.92
    999
    0.91
    ¢
    0.88
    %
    0.84
    %;
    0.82
     mph
    0.81
    %);
    0.79
    kHz
    0.78
    %,
    0.78
    Activations Density 0.064%

    No Known Activations