© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7496
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to the performance of baseball players

    oai_token-act-pair · gpt-3.5-turbo

    metrics related to baseball statistics, particularly earned run average (ERA) and on-base plus slugging (OPS)

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

    No Comments

    Negative Logits
    ridges
    -0.85
    don
    -0.76
    eret
    -0.75
    member
    -0.74
    alg
    -0.74
    stra
    -0.73
    azer
    -0.73
    rum
    -0.72
    dr
    -0.71
    real
    -0.71
    POSITIVE LOGITS
     ERA
    1.10
    BIP
    1.02
     pitched
    0.94
     reliever
    0.86
     fastball
    0.84
     pitcher
    0.81
     strugg
    0.80
     pitching
    0.79
     Rating
    0.78
     pitchers
    0.76
    Activations Density 0.014%

    No Known Activations