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. 9356
    Prev
    Next
    INDEX
    Explanations

    political candidates or individuals running for office

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating candidacy or electoral positions

    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
    ighed
    -0.85
    illin
    -0.74
    arity
    -0.73
    ivation
    -0.71
    lance
    -0.71
    breaks
    -0.71
    Scope
    -0.70
    venants
    -0.69
    ctic
    -0.69
    ern
    -0.69
    POSITIVE LOGITS
     nomination
    0.90
     Camel
    0.77
     consideration
    0.77
     reelection
    0.76
     ballot
    0.75
     captcha
    0.74
     supremacy
    0.74
     Nom
    0.73
     inclusion
    0.71
     whom
    0.70
    Activations Density 0.155%

    No Known Activations