© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10353
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events that continue or are ongoing

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing situations or trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.78
    ãĥĥãĥĪ
    -0.73
    axter
    -0.71
    liest
    -0.69
    arta
    -0.68
    etus
    -0.65
    arted
    -0.65
    iah
    -0.65
    ergic
    -0.64
    ĪĴ
    -0.61
    POSITIVE LOGITS
     unab
    1.21
     uninterrupted
    1.03
     indefinitely
    0.97
     unchanged
    0.96
     unanswered
    0.92
     unchecked
    0.91
     unresolved
    0.87
     throughout
    0.85
     till
    0.83
     unsolved
    0.80
    Activations Density 0.080%

    No Known Activations