© 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. 7-RES-JB
    11. 1713
    Prev
    Next
    INDEX
    Explanations

    signatures or credits at the end of documents or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and creators of works

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     mismatch
    -0.72
     fatig
    -0.68
     ditch
    -0.66
     smoking
    -0.66
     repeal
    -0.65
     filibuster
    -0.65
     unhealthy
    -0.64
    omin
    -0.63
     smoke
    -0.63
    oppers
    -0.62
    POSITIVE LOGITS
     Published
    0.89
    Edited
    0.87
     Architects
    0.84
     Edited
    0.82
    lain
    0.79
     ISBN
    0.78
     Scrib
    0.77
     Photography
    0.75
     Released
    0.75
     QC
    0.74
    Activations Density 0.382%

    No Known Activations