© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 613
    Prev
    Next
    INDEX
    Explanations

    mentions of specific soccer (football) managers

    oai_token-act-pair · gpt-3.5-turbo

    references to managers and their impact on team 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
    âĸ¬âĸ¬
    -0.91
    âĸ¬
    -0.87
     beads
    -0.86
     âĸ
    -0.85
     Budapest
    -0.83
     rotor
    -0.81
     ObamaCare
    -0.81
    glers
    -0.81
    Arizona
    -0.78
     MMR
    -0.78
    POSITIVE LOGITS
     Spurs
    2.31
     Tottenham
    1.79
    ottenham
    1.53
     Duncan
    1.53
     Poc
    1.43
     Bale
    1.32
     Maur
    1.19
     Gregg
    1.19
     Parker
    1.16
     Vill
    1.15
    Activations Density 0.110%

    No Known Activations