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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2-RES-JB
    6. 22592
    Prev
    Next
    INDEX
    Explanations

    information related to basketball players, specifically focusing on Kevin Durant

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific basketball players, particularly Kevin Durant and Russell Westbrook

    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
    gently
    -0.68
    course
    -0.68
    ttle
    -0.67
    advertisement
    -0.67
    ffic
    -0.66
    76561
    -0.65
    service
    -0.63
    resources
    -0.62
     Cosponsors
    -0.61
    INT
    -0.61
    POSITIVE LOGITS
     Durant
    1.00
     Westbrook
    0.94
     Harden
    0.90
     Bros
    0.78
    halla
    0.78
    minster
    0.74
    stadt
    0.73
    achev
    0.71
     Hots
    0.70
    endi
    0.69
    Activations Density 0.018%

    No Known Activations