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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11-RES-JB
    6. 4048
    Prev
    Next
    INDEX
    Explanations

    instances of words related to political campaigns and elections

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political candidacy or running for office

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.63
    ipop
    -0.61
    Birth
    -0.60
     Lod
    -0.59
     Uriel
    -0.55
    Bas
    -0.53
    oven
    -0.53
    olia
    -0.53
    theless
    -0.52
     wrought
    -0.52
    POSITIVE LOGITS
     mate
    1.11
     against
    1.01
     unsuccessfully
    0.93
     mates
    0.84
     af
    0.83
     candidacy
    0.81
     for
    0.81
     alongside
    0.80
    against
    0.78
    agate
    0.78
    Activations Density 0.037%

    No Known Activations