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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8258
    Prev
    Next
    INDEX
    Explanations

    adjectives related to gender characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to gender and the concepts of masculinity and femininity

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

    No Comments

    Negative Logits
    Assembly
    -0.77
    oulos
    -0.74
    akings
    -0.74
    Deal
    -0.72
    govtrack
    -0.71
    rella
    -0.70
    Sound
    -0.67
    rocket
    -0.67
    Chip
    -0.67
    eering
    -0.66
    POSITIVE LOGITS
     masculine
    0.98
     feminine
    0.95
    inity
    0.91
     femin
    0.91
     mascul
    0.88
    inant
    0.82
    istries
    0.82
     pronouns
    0.81
    atan
    0.80
     hygiene
    0.79
    Activations Density 0.018%

    No Known Activations