© 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. 8-RES-JB
    11. 2674
    Prev
    Next
    INDEX
    Explanations

    numerical values related to a baseball player's performance statistics

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to sports performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conting
    -0.69
    atom
    -0.67
    hod
    -0.65
     Lear
    -0.63
     Gum
    -0.63
     Ess
    -0.61
     Magnetic
    -0.61
    icians
    -0.60
     concess
    -0.60
    cit
    -0.60
    POSITIVE LOGITS
    uracy
    0.93
     squared
    0.81
     fastball
    0.76
     ERA
    0.75
     averaging
    0.74
    Stats
    0.74
    elsen
    0.74
    rafted
    0.73
    BIP
    0.73
    antage
    0.73
    Activations Density 0.134%

    No Known Activations