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. 0-RES-JB
    6. 17695
    Prev
    Next
    INDEX
    Explanations

    terms related to the sport of baseball

    oai_token-act-pair · gpt-3.5-turbo

    references to baseball

    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
     veil
    -0.82
    ess
    -0.68
     serpent
    -0.67
    dim
    -0.67
     facilit
    -0.65
     prim
    -0.65
    hent
    -0.64
     endanger
    -0.64
     ve
    -0.63
    orus
    -0.63
    POSITIVE LOGITS
     Baseball
    3.93
     Basketball
    2.00
     Soccer
    1.98
     Hockey
    1.84
     Cricket
    1.78
     baseball
    1.77
     MLB
    1.74
     Football
    1.73
     Wrestling
    1.72
     Tennis
    1.61
    Activations Density 0.010%

    No Known Activations