© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23640
    Prev
    Next
    INDEX
    Explanations

    keywords related to events or announcements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to events and societal issues involving resources or systems

    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
    enegger
    -0.89
    orically
    -0.76
    oulos
    -0.74
    ocate
    -0.73
    ngth
    -0.73
    arnaev
    -0.73
    nown
    -0.70
    ptin
    -0.69
    eger
    -0.68
    GGGGGGGG
    -0.67
    POSITIVE LOGITS
     occasions
    1.41
     basis
    1.05
     occasion
    0.95
     behalf
    0.95
     grounds
    0.90
     eve
    0.85
     shores
    0.85
    ilts
    0.84
     forums
    0.84
     fronts
    0.82
    Activations Density 0.343%

    No Known Activations