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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 13527
    Prev
    Next
    INDEX
    Explanations

    times, dates, and numerical data in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numeric data, particularly related to statistics and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blasting
    -0.59
    istries
    -0.56
     conservatives
    -0.54
    glas
    -0.53
    \",
    -0.53
    ffee
    -0.53
    hers
    -0.53
    ampunk
    -0.52
     charism
    -0.50
     uncond
    -0.50
    POSITIVE LOGITS
    OTAL
    0.96
    quished
    0.93
    cellaneous
    0.85
    Total
    0.76
     Includes
    0.74
     TOTAL
    0.71
    $$$$
    0.70
    Optional
    0.70
    unknown
    0.69
    Others
    0.68
    Activations Density 0.369%

    No Known Activations