© 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. 9991
    Prev
    Next
    INDEX
    Explanations

    items or concepts that have changed or improved over time

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods

    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
    bol
    -0.72
    locks
    -0.70
    username
    -0.69
    icious
    -0.67
    raught
    -0.65
     PLEASE
    -0.65
     inconsist
    -0.65
    _-
    -0.64
     topped
    -0.64
    $$$$
    -0.63
    POSITIVE LOGITS
     previous
    1.07
     neighboring
    0.85
     neighbouring
    0.79
     lieu
    0.79
    roads
    0.78
    clus
    0.76
     accordance
    0.74
     other
    0.73
     academia
    0.73
     1929
    0.72
    Activations Density 0.216%

    No Known Activations