© 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. 2-RES-JB
    11. 17802
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal or taboo relationships, specifically incest

    oai_token-act-pair · gpt-3.5-turbo

    references to incest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deen
    -0.77
    eem
    -0.74
    zl
    -0.72
    oÄŁ
    -0.71
    kinson
    -0.69
    ngth
    -0.69
    kar
    -0.68
    vich
    -0.67
    ez
    -0.67
    eting
    -0.66
    POSITIVE LOGITS
     incest
    1.17
    cest
    0.87
    uous
    0.82
     suff
    0.73
    opt
    0.72
    uring
    0.71
     coerc
    0.71
    ortium
    0.71
    itus
    0.70
     Consent
    0.70
    Activations Density 0.027%

    No Known Activations