© 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. 16608
    Prev
    Next
    INDEX
    Explanations

    mentions of soccer clubs and their players

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to football (soccer) players 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
     Cambod
    -0.97
    Indiana
    -0.94
     Buddha
    -0.93
     Blooming
    -0.89
    Samsung
    -0.88
     Hawai
    -0.88
     Fiji
    -0.88
    olulu
    -0.86
     resettlement
    -0.86
     Buddhist
    -0.86
    POSITIVE LOGITS
     Wenger
    2.37
     Arsenal
    2.25
    Arsenal
    2.19
     Ars
    1.97
     Emirates
    1.71
     Olivier
    1.34
     Theo
    1.33
     Alexis
    1.32
     Gun
    1.27
     Sanchez
    1.25
    Activations Density 0.117%

    No Known Activations