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. 14922
    Prev
    Next
    INDEX
    Explanations

    the word "man" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "man" and related expressions of masculinity

    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
    ADRA
    -0.73
    LCS
    -0.73
    PsyNetMessage
    -0.71
    Democratic
    -0.69
    RIPT
    -0.68
    ython
    -0.67
     Cosponsors
    -0.67
    IFT
    -0.65
    Detroit
    -0.63
    REDACTED
    -0.62
    POSITIVE LOGITS
    ifest
    1.13
    hunt
    1.07
    hood
    1.06
    fred
    1.02
    gling
    0.99
    hattan
    0.98
    agers
    0.95
    liness
    0.93
    oeuv
    0.92
    uscript
    0.92
    Activations Density 0.061%

    No Known Activations