© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 9782
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bipartisan" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to bipartisan support in political contexts

    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
    resp
    -0.82
    ques
    -0.81
    words
    -0.78
    ogenesis
    -0.77
    argon
    -0.76
    wright
    -0.75
    phal
    -0.75
    iph
    -0.75
    eon
    -0.74
    older
    -0.73
    POSITIVE LOGITS
     majorities
    1.02
     consensus
    0.99
     bipartisan
    0.95
     agreement
    0.89
     coalition
    0.87
     effort
    0.84
     congressional
    0.84
     efforts
    0.83
     minded
    0.82
    etooth
    0.81
    Activations Density 0.022%

    No Known Activations