© 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. 0-RES-JB
    11. 505
    Prev
    Next
    INDEX
    Explanations

    statistics or information related to sports, particularly baseball

    oai_token-act-pair · gpt-3.5-turbo

    references to baseball innings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Proud
    -0.76
    can
    -0.69
     CN
    -0.68
     Dra
    -0.65
    oke
    -0.64
    asc
    -0.64
    ophob
    -0.62
     Sorce
    -0.61
     Detect
    -0.60
    Know
    -0.59
    POSITIVE LOGITS
     innings
    3.76
     inning
    2.13
     strikeouts
    1.50
     bullpen
    1.49
     pitches
    1.34
     batters
    1.33
     pitchers
    1.33
     reliever
    1.32
     batting
    1.26
     outfield
    1.25
    Activations Density 0.007%

    No Known Activations