© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    mentions of main characters or central figures in a story

    oai_token-act-pair · gpt-3.5-turbo

    references to protagonists in narratives

    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
    dos
    -0.90
    orks
    -0.78
    itsch
    -0.76
    assic
    -0.75
    omin
    -0.72
    ensing
    -0.71
    spl
    -0.70
    imentary
    -0.68
    lic
    -0.68
    vette
    -0.67
    POSITIVE LOGITS
     protagonist
    1.32
     protagonists
    1.17
    acters
    1.12
     heroine
    1.10
     charact
    0.86
     unden
    0.83
     avatar
    0.77
     narrator
    0.76
     archetype
    0.75
     laureate
    0.75
    Activations Density 0.006%

    No Known Activations