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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 22288
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms related to various fields such as medicine, technology, and geology

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to scientific concepts and measurable phenomena

    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
     largeDownload
    -0.83
    ilver
    -0.76
    ecause
    -0.75
    ummer
    -0.74
    ync
    -0.73
    peed
    -0.73
    ensical
    -0.71
    ettings
    -0.71
    creen
    -0.69
    cale
    -0.68
    POSITIVE LOGITS
     count
    0.99
    pool
    0.99
     repertoire
    0.92
    elist
    0.92
     combinations
    0.90
     lineup
    0.89
     pools
    0.88
    ry
    0.88
     list
    0.88
     categories
    0.87
    Activations Density 0.553%

    No Known Activations