© 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. 10-RES-JB
    11. 12746
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political candidates and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cients
    -0.84
    ESE
    -0.80
    illet
    -0.73
    ento
    -0.71
    dx
    -0.69
     Intermediate
    -0.68
     Unch
    -0.66
     provinces
    -0.65
    âĵĺ
    -0.63
     inland
    -0.63
    POSITIVE LOGITS
     Barack
    1.48
     Donald
    1.44
     Oprah
    1.34
     Michael
    1.34
     Steve
    1.32
     Ronald
    1.30
     Vladimir
    1.30
     Jimmy
    1.29
     Hillary
    1.26
     Michelle
    1.25
    Activations Density 0.302%

    No Known Activations