© 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. 9962
    Prev
    Next
    INDEX
    Explanations

    instances of sports plays resulting in points or scores

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or movements associated with scoring in sports

    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
    behavior
    -0.72
    spect
    -0.69
    usage
    -0.68
    soType
    -0.66
    pmwiki
    -0.65
    consuming
    -0.65
    enforcement
    -0.64
    spection
    -0.64
     diction
    -0.64
    walking
    -0.61
    POSITIVE LOGITS
     propel
    1.13
     earn
    1.12
     clinch
    1.10
     seal
    1.09
     extend
    1.08
     erase
    1.07
     begin
    1.03
     tie
    0.99
     preserve
    0.98
     send
    0.97
    Activations Density 0.094%

    No Known Activations