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. 3-RES-JB
    6. 7983
    Prev
    Next
    INDEX
    Explanations

    the term "Big Ten"

    oai_token-act-pair · gpt-3.5-turbo

    references to college athletic conferences, particularly the Big Ten and Pac-12

    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
    ãĤ¨ãĥ«
    -0.79
     challeng
    -0.69
    respond
    -0.68
    PsyNetMessage
    -0.67
    aina
    -0.66
    perty
    -0.65
    acqu
    -0.64
    orders
    -0.64
     detained
    -0.63
    cia
    -0.63
    POSITIVE LOGITS
     Conference
    0.98
     Playoff
    0.97
     Wrestling
    0.95
     Tournament
    0.90
     Championship
    0.88
     Championships
    0.84
     Basketball
    0.82
     Showdown
    0.80
     Commission
    0.80
     Finals
    0.78
    Activations Density 0.052%

    No Known Activations