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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 22386
    Prev
    Next
    INDEX
    Explanations

    references to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to updates and reviews of various topics or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to times in news (referring to previous reports or upcoming coverage)

    Explanation Uploaded by User
    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
     alienated
    -0.64
     alienation
    -0.64
    âĹ¼
    -0.63
    uv
    -0.62
     implants
    -0.60
    het
    -0.59
    alien
    -0.58
    ophone
    -0.58
    æ©
    -0.58
    aft
    -0.57
    POSITIVE LOGITS
     Coverage
    1.01
     POLITICO
    0.93
     Updates
    0.92
     Updated
    0.91
     columns
    0.90
     updates
    0.89
     rundown
    0.89
     updated
    0.88
    updated
    0.87
     charts
    0.87
    Activations Density 1.027%

    No Known Activations