© 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. 7-RES-JB
    11. 13407
    Prev
    Next
    INDEX
    Explanations

    references to passing or crossing the ball in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports plays and assists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inction
    -0.73
    ersive
    -0.73
    netflix
    -0.73
    chwitz
    -0.72
    paio
    -0.71
     ageing
    -0.70
    asca
    -0.69
     Canaver
    -0.68
     learnt
    -0.68
     Scient
    -0.68
    POSITIVE LOGITS
     teammate
    0.95
     alley
    0.86
    hook
    0.84
     ball
    0.81
     scorer
    0.81
     teammates
    0.78
     scoring
    0.78
    tackle
    0.76
     groin
    0.76
     foul
    0.73
    Activations Density 0.285%

    No Known Activations