© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 12805
    Prev
    Next
    INDEX
    Explanations

    words related to performers in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to adult industry performers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.69
    ories
    -0.66
     annexation
    -0.64
     confirmation
    -0.62
    orgetown
    -0.62
     Bore
    -0.61
     bitterness
    -0.60
    ocide
    -0.60
     vengeance
    -0.59
     dissolution
    -0.59
    POSITIVE LOGITS
     contestant
    0.96
     contestants
    0.91
    glers
    0.91
     performers
    0.79
    Artist
    0.77
    rities
    0.77
    esses
    0.74
    encies
    0.73
     performer
    0.73
     laureate
    0.72
    Activations Density 0.017%

    No Known Activations