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. 9-RES-JB
    6. 16877
    Prev
    Next
    INDEX
    Explanations

    mentions of basketball-related terms related to shooting and athletic abilities

    oai_token-act-pair · gpt-3.5-turbo

    references to athletic skills and abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABE
    -0.89
     Seat
    -0.82
     Administ
    -0.77
     Anne
    -0.69
    arantine
    -0.68
     Funding
    -0.68
     Advertising
    -0.65
     Chair
    -0.64
     Banner
    -0.64
    ENTS
    -0.63
    POSITIVE LOGITS
     athleticism
    1.08
     athlet
    1.08
     offensively
    1.05
     prowess
    1.01
     skills
    0.99
     tendencies
    0.97
     versatility
    0.96
     repertoire
    0.95
    uracy
    0.92
     talent
    0.92
    Activations Density 0.242%

    No Known Activations