© 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. 2-RES-JB
    11. 23978
    Prev
    Next
    INDEX
    Explanations

    words related to specific sports positions, particularly the position of a baseball pitcher

    oai_token-act-pair · gpt-3.5-turbo

    references to pitchers in baseball

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dhabi
    -0.81
    orate
    -0.80
    isec
    -0.75
    ë
    -0.74
    innie
    -0.74
    atche
    -0.73
    redit
    -0.73
    hem
    -0.72
    ourgeois
    -0.71
    aff
    -0.70
    POSITIVE LOGITS
     pitcher
    1.27
     pitchers
    1.17
     reliever
    0.90
     catcher
    0.87
     RHP
    0.85
     pitching
    0.83
     Adin
    0.80
     ERA
    0.78
    hander
    0.78
     Slug
    0.77
    Activations Density 0.014%

    No Known Activations