© 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. 9-RES-JB
    11. 7567
    Prev
    Next
    INDEX
    Explanations

    physical actions related to force and coercion

    oai_token-act-pair · gpt-3.5-turbo

    references to male characters and their actions in a context of aggression or dominance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Period
    -0.69
    CNN
    -0.68
     Gleaming
    -0.68
     Actress
    -0.67
     Bundes
    -0.66
    clude
    -0.61
    nb
    -0.61
     Codex
    -0.60
     herself
    -0.59
     Berm
    -0.59
    POSITIVE LOGITS
     ejac
    0.95
     penis
    0.91
     circumcised
    0.86
     masturb
    0.82
     semen
    0.81
    ctor
    0.77
     handsome
    0.76
    venants
    0.75
    enegger
    0.75
    panic
    0.73
    Activations Density 0.323%

    No Known Activations