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. 4-RES-JB
    6. 8776
    Prev
    Next
    INDEX
    Explanations

    words related to political campaigns and presidential bids

    oai_token-act-pair · gpt-3.5-turbo

    terms related to presidential campaigns and bids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Production
    -0.77
    onal
    -0.66
    DEP
    -0.63
    idious
    -0.63
    MpServer
    -0.63
     frust
    -0.63
    Sym
    -0.63
    Property
    -0.62
    skilled
    -0.61
    lass
    -0.61
    POSITIVE LOGITS
     Camel
    0.69
    ¯
    0.69
    eering
    0.68
    ebus
    0.67
    robe
    0.67
     Writ
    0.65
    visor
    0.65
    dq
    0.65
    olicy
    0.64
     Narendra
    0.64
    Activations Density 0.046%

    No Known Activations