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. 5508
    Prev
    Next
    INDEX
    Explanations

    phrases related to men's issues or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to gender-related topics, specifically focusing on women's issues

    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
    SIGN
    -0.73
    OVER
    -0.66
     snail
    -0.63
    ļéĨĴ
    -0.60
     Leilan
    -0.58
    SET
    -0.57
     commons
    -0.56
     Heist
    -0.55
    EStream
    -0.55
     Presidents
    -0.54
    POSITIVE LOGITS
    atisf
    1.02
    kaya
    0.93
    outhern
    0.91
    lightly
    0.90
    pecially
    0.90
    wered
    0.89
    atellite
    0.89
    bestos
    0.89
    ween
    0.87
    omew
    0.87
    Activations Density 0.190%

    No Known Activations