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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 20004
    Prev
    Next
    INDEX
    Explanations

    references to male-related concepts or gender-specific terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "male" in various contexts related to gender dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVERS
    -0.70
    uilt
    -0.70
     GOODMAN
    -0.69
    ovie
    -0.69
    Deal
    -0.68
    krit
    -0.67
    ravel
    -0.66
     Manufacturer
    -0.66
    rep
    -0.64
    overed
    -0.64
    POSITIVE LOGITS
    volent
    1.99
    vol
    1.10
     genital
    1.03
     ejac
    0.92
     infertility
    0.90
     genitals
    0.86
     supremacists
    0.84
    vich
    0.83
     anatomy
    0.79
     supremacist
    0.79
    Activations Density 0.025%

    No Known Activations