© 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. 10-RES-JB
    11. 16256
    Prev
    Next
    INDEX
    Explanations

    names of football players and clubs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of football teams and players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     federally
    -0.99
     statewide
    -0.88
     Appalach
    -0.86
    achusetts
    -0.86
    umblr
    -0.86
     thru
    -0.85
    entanyl
    -0.84
     Cherokee
    -0.83
     opioid
    -0.82
     Appalachian
    -0.81
    POSITIVE LOGITS
     Juventus
    1.92
     Barcelona
    1.83
     Messi
    1.83
     Ronaldo
    1.77
     Madrid
    1.73
     Guardiola
    1.73
     Bayern
    1.71
     Serie
    1.67
     Mourinho
    1.66
     UEFA
    1.66
    Activations Density 0.648%

    No Known Activations