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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5707
    Prev
    Next
    INDEX
    Explanations

    gender-related characteristics and attributes, such as masculinity and femininity

    oai_token-act-pair · gpt-3.5-turbo

    terms that represent gender concepts, specifically masculinity and femininity

    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
    oulos
    -0.83
    Assembly
    -0.81
    rocket
    -0.75
    Deal
    -0.74
    owitz
    -0.72
    Money
    -0.68
     Redemption
    -0.68
    RAY
    -0.68
    DVD
    -0.67
    REL
    -0.66
    POSITIVE LOGITS
     hygiene
    0.96
     masculine
    0.90
     feminine
    0.88
     pronouns
    0.87
     femin
    0.82
    istries
    0.80
     masculinity
    0.79
    inity
    0.78
     mascul
    0.77
    WithNo
    0.76
    Activations Density 0.036%

    No Known Activations