© 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. 1-RES-JB
    11. 3290
    Prev
    Next
    INDEX
    Explanations

    words related to 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.91
    imentary
    -0.80
    independent
    -0.77
    olen
    -0.75
    ateur
    -0.73
    pora
    -0.69
    ongyang
    -0.69
    emporary
    -0.68
    ntil
    -0.67
    ighton
    -0.67
    POSITIVE LOGITS
     hero
    1.27
     heroine
    1.12
     heroes
    1.06
    Hero
    0.98
    hero
    0.97
     protagonist
    0.93
     Hero
    0.82
    士
    0.81
    ically
    0.79
    rities
    0.76
    Activations Density 0.008%

    No Known Activations