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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 12639
    Prev
    Next
    INDEX
    Explanations

    instances of talk about potential candidacies for political office

    oai_token-act-pair · gpt-3.5-turbo

    references to political candidacy or electoral intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fect
    -0.66
    rehens
    -0.64
     ERROR
    -0.63
     Deaths
    -0.62
    Express
    -0.62
     Authority
    -0.62
    Reason
    -0.61
    ECA
    -0.61
    had
    -0.60
    eyed
    -0.59
    POSITIVE LOGITS
     resume
    0.80
     relocate
    0.79
    morrow
    0.73
     sooner
    0.70
    soDeliveryDate
    0.68
     revert
    0.67
     someday
    0.67
     hous
    0.66
     renegoti
    0.66
     rethink
    0.65
    Activations Density 0.887%

    No Known Activations