© 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. 6-RES-JB
    11. 4253
    Prev
    Next
    INDEX
    Explanations

    titles or headings in a written document

    oai_token-act-pair · gpt-3.5-turbo

    formatting indicators and references related to articles and media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ïī
    -0.66
    gd
    -0.64
    paces
    -0.63
     pow
    -0.61
    pas
    -0.60
    perature
    -0.59
    pheus
    -0.59
    .","
    -0.57
     disg
    -0.57
    antage
    -0.56
    POSITIVE LOGITS
     Description
    0.91
     Summary
    0.91
     Categories
    0.87
     Extras
    0.84
     Features
    0.82
     Details
    0.78
     Facts
    0.76
     References
    0.76
    icularly
    0.75
     Comparison
    0.74
    Activations Density 0.252%

    No Known Activations