© 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. 2639
    Prev
    Next
    INDEX
    Explanations

    instances of specific numbers, such as ages, times, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities, relational terms, or degrees of existence

    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
    "))
    -0.67
     tyr
    -0.57
     Defin
    -0.55
     acknow
    -0.54
    Sund
    -0.53
     fitt
    -0.53
     happ
    -0.52
    aughed
    -0.46
     varied
    -0.46
    "),
    -0.46
    POSITIVE LOGITS
    .
    1.03
    ,.
    1.01
    .,
    1.00
    ,
    0.97
    *.
    0.86
    .[
    0.85
     respectively
    0.84
    _.
    0.83
    .''.
    0.81
    !.
    0.81
    Activations Density 0.452%

    No Known Activations