© 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. 1058
    Prev
    Next
    INDEX
    Explanations

    keywords related to characters or personas

    oai_token-act-pair · gpt-3.5-turbo

    references to characters in narratives or games

    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
    ainer
    -0.79
    tesy
    -0.72
    ral
    -0.71
    washer
    -0.70
    vice
    -0.66
    jury
    -0.65
    loader
    -0.65
    usted
    -0.64
    ledge
    -0.63
     Exercise
    -0.63
    POSITIVE LOGITS
     characters
    3.73
     Characters
    3.03
    Characters
    2.57
     character
    2.42
     protagonists
    2.09
    acters
    2.07
    Character
    1.84
     Character
    1.79
     charact
    1.78
    character
    1.77
    Activations Density 0.025%

    No Known Activations