Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9657
    Prev
    Next
    INDEX
    Explanations

    mentions of gender, specifically focusing on males

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "male."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.80
    krit
    -0.77
    heet
    -0.75
    etsk
    -0.73
    leans
    -0.72
    arella
    -0.69
    rep
    -0.69
    duration
    -0.68
    xtap
    -0.66
    today
    -0.66
    POSITIVE LOGITS
    volent
    1.84
     genital
    1.01
    vol
    0.97
     ejac
    0.93
     genitals
    0.88
     infertility
    0.85
     supremacy
    0.81
     circumcision
    0.79
     supremacist
    0.79
     reproductive
    0.78
    Activations Density 0.018%

    No Known Activations