© 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. 1-RES-JB
    11. 11467
    Prev
    Next
    INDEX
    Explanations

    terms related to mutation or mutilation, especially in the context of sexual organs

    oai_token-act-pair · gpt-3.5-turbo

    references to mutilation, particularly in the context of female genital mutilation and related violent practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Defenders
    -0.88
    ulhu
    -0.75
    ctica
    -0.72
    ¯¯
    -0.71
    ngth
    -0.68
    itton
    -0.66
    OPLE
    -0.65
    zzi
    -0.64
    æ©Ł
    -0.64
    zona
    -0.64
    POSITIVE LOGITS
     mut
    1.03
    Mut
    0.92
    iple
    0.91
    mut
    0.85
    ually
    0.84
    iny
    0.82
    iously
    0.80
    rats
    0.78
    tering
    0.78
    ilation
    0.76
    Activations Density 0.005%

    No Known Activations