© 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. 1754
    Prev
    Next
    INDEX
    Explanations

    dates, events, and official announcements

    oai_token-act-pair · gpt-3.5-turbo

    significant events or announcements related to government or organizational decisions

    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
    ibles
    -0.56
     wont
    -0.56
     depends
    -0.55
    Others
    -0.55
     doesnt
    -0.53
     varies
    -0.53
     anyways
    -0.53
     dont
    -0.53
     strives
    -0.52
     begs
    -0.52
    POSITIVE LOGITS
    ixty
    0.63
    FTWARE
    0.57
    itled
    0.56
    schild
    0.55
     subpoen
    0.55
    earable
    0.52
     suing
    0.52
     Canaver
    0.51
     announcing
    0.49
    otom
    0.49
    Activations Density 1.202%

    No Known Activations