© 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. 4-RES-JB
    11. 24029
    Prev
    Next
    INDEX
    Explanations

    mentions of specific states in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to states in the context of political elections

    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
    ogle
    -0.85
    oice
    -0.74
    ammers
    -0.73
    imet
    -0.73
    hran
    -0.71
    emis
    -0.71
    berus
    -0.71
    alid
    -0.68
    nob
    -0.67
    uggish
    -0.66
    POSITIVE LOGITS
    wide
    0.99
     legislatures
    0.90
     electorate
    0.88
     legislature
    0.80
     Democratic
    0.77
     parks
    0.73
     Legislature
    0.73
     legalized
    0.73
     Governor
    0.73
     elector
    0.72
    Activations Density 0.071%

    No Known Activations