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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 18790
    Prev
    Next
    INDEX
    Explanations

    mentions of bipartisan efforts or agreements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bipartisan support or actions in political contexts

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

    No Comments

    Negative Logits
    resp
    -0.89
    wright
    -0.77
    words
    -0.76
    ulia
    -0.76
    eon
    -0.76
    ques
    -0.74
    uv
    -0.72
    laus
    -0.71
    alon
    -0.70
    argon
    -0.69
    POSITIVE LOGITS
     bipartisan
    0.98
     majorities
    0.95
     consensus
    0.93
     coalition
    0.86
     minded
    0.83
     efforts
    0.82
    etooth
    0.81
     initiatives
    0.80
     congressional
    0.80
     effort
    0.78
    Activations Density 0.011%

    No Known Activations