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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4913
    Prev
    Next
    INDEX
    Explanations

    descriptions related to sports actions, especially shots and goals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to shots or attempts made in a sporting context

    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
    iatus
    -0.74
    FY
    -0.70
     Caucus
    -0.68
    cius
    -0.66
    DAQ
    -0.66
    -$
    -0.66
     statewide
    -0.65
     OPS
    -0.65
     Tribal
    -0.64
     Summit
    -0.64
    POSITIVE LOGITS
     volley
    0.93
     brilliantly
    0.91
     curled
    0.85
     goalkeeper
    0.84
     Gael
    0.84
     fingert
    0.82
     keeper
    0.81
     header
    0.80
    Liverpool
    0.79
     unmarked
    0.79
    Activations Density 0.108%

    No Known Activations