© 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. 0-RES-JB
    11. 22191
    Prev
    Next
    INDEX
    Explanations

    words related to characters in a narrative, such as protagonist and antagonist

    oai_token-act-pair · gpt-3.5-turbo

    terms related to protagonists and their roles in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERG
    -0.84
    estyle
    -0.67
    ools
    -0.65
    etry
    -0.65
    Fit
    -0.65
     mosques
    -0.64
    GB
    -0.64
     golf
    -0.64
    rees
    -0.63
    fg
    -0.63
    POSITIVE LOGITS
     protagonist
    3.34
     narrator
    3.13
     protagonists
    2.31
     heroine
    2.20
    agonist
    1.84
     antagonist
    1.72
     frontman
    1.55
     narr
    1.49
     narration
    1.46
     trope
    1.35
    Activations Density 0.029%

    No Known Activations