© 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. 7-RES-JB
    11. 14241
    Prev
    Next
    INDEX
    Explanations

    references to awards or recognitions related to sports or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to award-winning players in sports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    heet
    -0.91
    rams
    -0.89
    orship
    -0.89
    ether
    -0.85
    hers
    -0.80
    perm
    -0.79
    uits
    -0.74
    oring
    -0.74
    etting
    -0.74
    esting
    -0.73
    POSITIVE LOGITS
    hood
    1.01
    Rank
    0.95
    stown
    0.95
    Unknown
    0.92
    unknown
    0.92
     Guides
    0.83
     Aid
    0.82
     Maker
    0.81
    Kind
    0.80
     Perspect
    0.80
    Activations Density 0.198%

    No Known Activations