© 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. 11-RES-JB
    11. 18819
    Prev
    Next
    INDEX
    Explanations

    politicians' names and political figures related to conservative politics

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent political figures and leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kru
    -0.66
     Hurricanes
    -0.57
     deduction
    -0.57
    à¨
    -0.57
     Fargo
    -0.56
     Coyotes
    -0.56
     Seah
    -0.54
     Ruins
    -0.54
     Viper
    -0.53
     Crescent
    -0.53
    POSITIVE LOGITS
     Jr
    1.18
     Sr
    0.92
     III
    0.88
     whom
    0.86
    agher
    0.85
    Jr
    0.80
     alike
    0.73
     who
    0.71
     aka
    0.70
     respectively
    0.69
    Activations Density 0.218%

    No Known Activations