© 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. 15712
    Prev
    Next
    INDEX
    Explanations

    numerical statistics such as scores, yardage, points, and plays in sports

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" with varying contexts or scores

    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
    Allah
    -0.78
    ptin
    -0.73
    usercontent
    -0.70
    NESS
    -0.66
    soDeliveryDate
    -0.65
    20439
    -0.64
    peer
    -0.63
    YY
    -0.63
    plin
    -0.62
    anse
    -0.61
    POSITIVE LOGITS
    etime
    1.03
     behalf
    0.92
     offense
    0.92
     occasion
    0.88
     penalties
    0.84
     Saturday
    0.83
     Opening
    0.82
     aggregate
    0.82
     purpose
    0.82
     downs
    0.81
    Activations Density 0.067%

    No Known Activations