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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 21085
    Prev
    Next
    INDEX
    Explanations

    sports-related terms such as names of teams, leagues, championships, and years

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific sports events, leagues, and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -1.00
    heit
    -0.78
    EVA
    -0.75
     whilst
    -0.73
    aram
    -0.73
    soDeliveryDate
    -0.70
    conom
    -0.70
    Sov
    -0.69
    bush
    -0.68
    oros
    -0.68
    POSITIVE LOGITS
     league
    1.34
     NCAA
    1.33
     NBA
    1.30
     NFL
    1.29
     sport
    1.28
     Bruins
    1.18
     Ducks
    1.15
     Sixers
    1.15
     Dodgers
    1.15
     Celtics
    1.15
    Activations Density 0.347%

    No Known Activations