© 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. 3-RES-JB
    11. 6434
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic disciplines, specifically "Political Science."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political science and academia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aways
    -0.71
    alogue
    -0.65
    together
    -0.63
    mates
    -0.63
    RGB
    -0.63
    inous
    -0.62
     genetically
    -0.61
    abouts
    -0.61
     unilaterally
    -0.60
    genic
    -0.58
    POSITIVE LOGITS
    fare
    0.77
     Consulting
    0.74
     lawy
    0.74
     Journalism
    0.72
     consultancy
    0.71
     Oversight
    0.70
     Reform
    0.70
    Crunch
    0.69
     Reporting
    0.69
     Journals
    0.68
    Activations Density 0.130%

    No Known Activations