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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7599
    Prev
    Next
    INDEX
    Explanations

    specific dates, numbers, and locations

    oai_token-act-pair · gpt-3.5-turbo

    key details pertaining to sports history and player statistics

    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
    ebin
    -0.76
    aspx
    -0.69
    entimes
    -0.69
    Uber
    -0.67
    2017
    -0.65
     ðŁĺ
    -0.65
    alon
    -0.63
     Patreon
    -0.63
    redd
    -0.63
     tweeting
    -0.62
    POSITIVE LOGITS
     Yugoslavia
    0.88
     1954
    0.83
    oslov
    0.83
     1964
    0.82
     Grateful
    0.78
     Commodore
    0.77
     1966
    0.76
     USSR
    0.76
     1955
    0.76
     Babe
    0.75
    Activations Density 0.958%

    No Known Activations