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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11278
    Prev
    Next
    INDEX
    Explanations

    descriptions of soccer plays, including shots, headers, crosses, goals, saves, and other soccer-related actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to sports actions and scoring events

    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
     secretive
    -0.64
    neys
    -0.59
    soever
    -0.59
    izoph
    -0.59
     interviewed
    -0.58
     <=
    -0.58
    bestos
    -0.57
     standardized
    -0.57
     vacations
    -0.57
    "],"
    -0.57
    POSITIVE LOGITS
     midway
    1.21
     moments
    0.99
     shortly
    0.89
     seconds
    0.87
     late
    0.85
     courtesy
    0.82
     momentarily
    0.82
     Moments
    0.82
     early
    0.81
     before
    0.80
    Activations Density 0.165%

    No Known Activations