© 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. 8-RES-JB
    11. 1326
    Prev
    Next
    INDEX
    Explanations

    words related to restructuring or rest, possibly in terms of finances or organization

    oai_token-act-pair · gpt-3.5-turbo

    references to restrictions or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itable
    -0.72
    ggle
    -0.69
    kers
    -0.66
    fortune
    -0.63
    itably
    -0.62
    itability
    -0.60
     Kushner
    -0.60
     Portuguese
    -0.60
    cles
    -0.58
    >>>>>>>>
    -0.58
    POSITIVE LOGITS
    ricted
    1.44
    raint
    1.43
    ricting
    1.43
    riction
    1.40
    rained
    1.38
    rict
    1.32
    raints
    1.26
    aur
    1.26
    raining
    1.13
    orative
    1.08
    Activations Density 0.038%

    No Known Activations