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. 9-RES-JB
    6. 12277
    Prev
    Next
    INDEX
    Explanations

    mentions of the number of points in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports standings and points

    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
    milo
    -0.76
     concess
    -0.70
    mob
    -0.69
    obyl
    -0.69
    umbn
    -0.68
     Peck
    -0.68
     mascul
    -0.67
    igmat
    -0.64
    amination
    -0.64
    mpeg
    -0.64
    POSITIVE LOGITS
     standings
    1.22
     unbeaten
    1.03
     undefeated
    1.00
     playoff
    0.93
     cellar
    0.91
     relegation
    0.90
     seeded
    0.83
     AFC
    0.82
     bye
    0.80
     Playoff
    0.80
    Activations Density 0.302%

    No Known Activations