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. 14234
    Prev
    Next
    INDEX
    Explanations

    names of political figures, particularly focusing on the last name "Gingrich."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Newt Gingrich

    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
    ournal
    -0.84
    pee
    -0.73
    ¥µ
    -0.71
    Constructed
    -0.70
    asca
    -0.70
    ĸļ
    -0.67
    raints
    -0.67
    ordering
    -0.65
    ĻĤ
    -0.64
    ivated
    -0.64
    POSITIVE LOGITS
     Gingrich
    1.30
    etz
    0.80
    enstein
    0.76
     MEP
    0.72
    ulation
    0.72
    ulations
    0.72
    mann
    0.71
     Romney
    0.69
     Cain
    0.69
    auld
    0.68
    Activations Density 0.014%

    No Known Activations