© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    words related to the position of **pitcher** in baseball

    oai_token-act-pair · gpt-3.5-turbo

    references to baseball pitchers and related accolades

    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
    ovo
    -0.79
    arch
    -0.71
     Independent
    -0.70
    redits
    -0.70
    â
    -0.70
    ï
    -0.68
    ë
    -0.68
     0000
    -0.66
    alf
    -0.66
    redit
    -0.66
    POSITIVE LOGITS
     pitcher
    3.57
     pitchers
    3.40
     reliever
    2.19
     pitching
    2.13
     catcher
    1.95
     RHP
    1.91
     bullpen
    1.86
     hitters
    1.84
     hitter
    1.83
     batters
    1.82
    Activations Density 0.014%

    No Known Activations