© 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. 20488
    Prev
    Next
    INDEX
    Explanations

    event locations and times

    oai_token-act-pair · gpt-3.5-turbo

    references to locations, dates, and associated event details

    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
     disg
    -0.74
     Haram
    -0.71
    kef
    -0.71
     .)
    -0.70
     circumcised
    -0.68
    oÄŁ
    -0.67
     fung
    -0.67
    icro
    -0.61
    opian
    -0.60
     ).
    -0.60
    POSITIVE LOGITS
    %:
    1.18
    :
    0.90
    ":"
    0.84
    iculty
    0.84
    ":{"
    0.78
    :"
    0.78
    ':
    0.77
    Synopsis
    0.77
     Prediction
    0.75
    Date
    0.75
    Activations Density 0.178%

    No Known Activations