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. 3-RES-JB
    6. 7643
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to the position of "center" in sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports positions, particularly in hockey and basketball

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Interactive
    -0.78
     Cheong
    -0.75
    riott
    -0.71
    reath
    -0.69
    ingu
    -0.66
     BIT
    -0.66
     RESP
    -0.65
     Bezos
    -0.65
    sth
    -0.64
    wcsstore
    -0.63
    POSITIVE LOGITS
     rookie
    1.03
     rookies
    1.01
     league
    0.98
     winger
    0.97
     fullback
    0.96
     linebacker
    0.96
     coach
    0.96
     leagues
    0.95
     offseason
    0.92
     outfield
    0.92
    Activations Density 0.265%

    No Known Activations