© 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. 1802
    Prev
    Next
    INDEX
    Explanations

    references to upgrades or offers for upgrades

    oai_token-act-pair · gpt-3.5-turbo

    references to upgrades or enhancements

    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
    bered
    -0.77
    otropic
    -0.72
    zman
    -0.68
    LESS
    -0.68
     Caption
    -0.67
    tering
    -0.67
    pal
    -0.67
     Unch
    -0.66
    SELECT
    -0.65
    avery
    -0.65
    POSITIVE LOGITS
    grades
    0.97
    ments
    0.96
    grading
    0.92
     upgrades
    0.89
    xual
    0.84
    graded
    0.82
    mentation
    0.82
     upgrade
    0.78
    IOR
    0.72
     upgrading
    0.71
    Activations Density 0.037%

    No Known Activations