© 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. 11-RES-JB
    11. 10040
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month and year

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.72
    llan
    -0.71
    antry
    -0.70
    onics
    -0.68
    Lago
    -0.67
    upon
    -0.67
    driving
    -0.66
    ERC
    -0.65
    ITH
    -0.64
    burg
    -0.63
    POSITIVE LOGITS
     Favorite
    0.73
     October
    0.73
     Average
    0.71
     December
    0.69
     September
    0.69
     Discuss
    0.68
     Subscribe
    0.66
     Select
    0.66
    isode
    0.66
     1989
    0.62
    Activations Density 0.041%

    No Known Activations