© 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. 7132
    Prev
    Next
    INDEX
    Explanations

    phrases related to soccer plays and scoring

    oai_token-act-pair · gpt-3.5-turbo
    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
    pkg
    -0.79
    Introduced
    -0.74
    Edited
    -0.67
     autom
    -0.63
    wcs
    -0.60
     hormones
    -0.59
    Girls
    -0.59
    Write
    -0.57
     embodiments
    -0.57
     Investig
    -0.57
    POSITIVE LOGITS
     midfield
    1.01
     goal
    0.94
     goalkeeper
    0.88
     center
    0.83
     centre
    0.81
     bounds
    0.78
     teammate
    0.77
    center
    0.75
     Goal
    0.75
     defender
    0.75
    Activations Density 0.101%

    No Known Activations