© 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. 2-RES-JB
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    references to heroes or heroic figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Hero" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.81
    choes
    -0.81
    ĸļ
    -0.78
    rup
    -0.75
    creen
    -0.75
    ounter
    -0.72
    model
    -0.66
    rupulous
    -0.66
    cling
    -0.66
    gdala
    -0.66
    POSITIVE LOGITS
    Hero
    0.96
     Offline
    0.75
    ic
    0.75
    iazep
    0.74
    osate
    0.73
     Fighters
    0.73
     Hero
    0.73
    adelphia
    0.72
    blade
    0.70
    inic
    0.69
    Activations Density 0.017%

    No Known Activations