© 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. 20795
    Prev
    Next
    INDEX
    Explanations

    terms related to various topics like medium, future, sports, laws, revolution, structures, class, eclipse, celebrities, lives, crisis, sport, and the Taliban

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to media, governance, and societal issues

    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
     pestic
    -0.73
    ucket
    -0.55
    ofi
    -0.53
    taboola
    -0.52
    doi
    -0.52
     Lash
    -0.51
     commenter
    -0.51
    arij
    -0.50
    ItemImage
    -0.49
     Alam
    -0.49
    POSITIVE LOGITS
     anymore
    0.82
     someday
    0.81
     instead
    0.79
     responsibly
    0.78
    .).
    0.77
     anew
    0.77
     ASAP
    0.74
     sooner
    0.74
     forever
    0.73
    .'
    0.73
    Activations Density 0.875%

    No Known Activations