© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 18757
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to American football statistics

    oai_token-act-pair · gpt-3.5-turbo

    statistical metrics related to sports performance

    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
     Belarus
    -0.85
     separatists
    -0.85
     separatist
    -0.82
    Ukraine
    -0.76
     Bosnia
    -0.75
    ctica
    -0.75
     sovere
    -0.75
     plur
    -0.75
    uders
    -0.75
     Yugoslavia
    -0.73
    POSITIVE LOGITS
     receptions
    1.47
     receivers
    1.42
     WR
    1.42
     receiver
    1.42
     backfield
    1.33
     Receiver
    1.30
     touchdowns
    1.28
     RB
    1.25
     touchdown
    1.22
     catches
    1.20
    Activations Density 0.335%

    No Known Activations