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

    Neuronpedia

    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. 10-RES-JB
    11. 12392
    Prev
    Next
    INDEX
    Explanations

    news-related content such as reports, findings, statements, and updates

    oai_token-act-pair · gpt-3.5-turbo

    reports from news sources

    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
    Generic
    -0.73
    orate
    -0.63
     CCP
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
     emptiness
    -0.61
     residues
    -0.60
     motivational
    -0.60
     Stall
    -0.60
    izable
    -0.59
    Termin
    -0.59
    POSITIVE LOGITS
     reporting
    1.11
     reporter
    1.09
     coverage
    1.08
     Coverage
    1.04
    reporting
    0.96
     uncover
    0.94
     reporters
    0.94
     scoop
    0.92
     correspondent
    0.92
     Pulitzer
    0.91
    Activations Density 0.330%

    No Known Activations