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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19513
    Prev
    Next
    INDEX
    Explanations

    the positions in American football and baseball where players are positioned

    oai_token-act-pair · gpt-3.5-turbo

    terms related to football positions, particularly cornerbacks and to a lesser extent, shortstops and defensemen in sports contexts

    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
    estone
    -0.77
    emon
    -0.74
    vg
    -0.73
    chn
    -0.71
    arist
    -0.71
    emb
    -0.71
    itia
    -0.69
    abet
    -0.68
    eln
    -0.67
    erer
    -0.67
    POSITIVE LOGITS
     cornerback
    1.10
     linebacker
    0.82
     outfielder
    0.75
     infield
    0.71
     shortstop
    0.70
     Franch
    0.68
     defender
    0.67
     Jagu
    0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.65
    è»
    0.65
    Activations Density 0.007%

    No Known Activations