Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12115
    Prev
    Next
    INDEX
    Explanations

    references to the word "pitcher" in the context of baseball

    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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dhabi
    -0.78
    alf
    -0.76
    orate
    -0.74
    ë
    -0.73
    atche
    -0.72
    redit
    -0.72
    ourgeois
    -0.71
    hem
    -0.71
    isec
    -0.70
    arl
    -0.68
    POSITIVE LOGITS
     pitcher
    1.35
     pitchers
    1.33
     catcher
    0.94
     reliever
    0.93
     RHP
    0.89
     outfielder
    0.87
    hander
    0.85
     mound
    0.84
     shortstop
    0.83
     batters
    0.82
    Activations Density 0.009%

    No Known Activations