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. 8068
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to males, particularly starting with the word "he"

    oai_token-act-pair · gpt-3.5-turbo

    references to a male individual

    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
     Seym
    -0.72
    emale
    -0.70
    etheless
    -0.66
    raints
    -0.57
    igslist
    -0.57
    flix
    -0.56
     constit
    -0.55
    terms
    -0.54
    deen
    -0.52
    execute
    -0.52
    POSITIVE LOGITS
    zbollah
    0.91
    mos
    0.77
     Majesty
    0.75
    eded
    0.73
    sych
    0.67
    dor
    0.66
    brew
    0.65
    sing
    0.65
    'd
    0.64
    ALTH
    0.64
    Activations Density 0.252%

    No Known Activations