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. 9-RES-JB
    6. 10277
    Prev
    Next
    INDEX
    Explanations

    references to movements and changes of positions in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    details about player positions and movements in sports contexts

    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
     Congratulations
    -0.82
    worthiness
    -0.74
     Merchants
    -0.70
     Lifetime
    -0.68
    valid
    -0.68
     Generations
    -0.67
     Achievement
    -0.67
     Curiosity
    -0.67
     resear
    -0.66
     Yelp
    -0.65
    POSITIVE LOGITS
     midfield
    1.37
     fullback
    1.30
     backfield
    1.18
     flank
    1.14
     outfield
    1.13
     winger
    1.11
     role
    1.10
     pivot
    1.08
     wing
    1.07
     frontline
    1.06
    Activations Density 0.549%

    No Known Activations