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. 9-RES-JB
    6. 21637
    Prev
    Next
    INDEX
    Explanations

    names of political figures and governmental entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and significant geopolitical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.84
    anian
    -0.82
    "}],"
    -0.67
    .","
    -0.64
    å°Ĩ
    -0.64
    bral
    -0.63
    "}
    -0.62
    partisan
    -0.62
    gru
    -0.60
    andom
    -0.60
    POSITIVE LOGITS
     JFK
    0.66
     TBA
    0.65
     La
    0.65
     Chick
    0.64
     Cla
    0.64
     Dak
    0.61
     Olymp
    0.61
     Cad
    0.61
     Uran
    0.61
     Et
    0.60
    Activations Density 0.800%

    No Known Activations