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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7478
    Prev
    Next
    INDEX
    Explanations

    phrases related to the politician Newt 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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.72
    LESS
    -0.66
    idas
    -0.63
    ————————————————
    -0.62
    ĻĤ
    -0.60
    raints
    -0.60
    Gas
    -0.59
    psc
    -0.59
    ++++++++++++++++
    -0.59
    ition
    -0.59
    POSITIVE LOGITS
     Gingrich
    1.23
    etz
    0.87
    enstein
    0.79
    mann
    0.74
     tracts
    0.71
    zilla
    0.70
    indal
    0.68
    ervative
    0.68
    osponsors
    0.67
    ulations
    0.67
    Activations Density 0.012%

    No Known Activations