© 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. 2-RES-JB
    11. 9352
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sanders"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Sanders."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocard
    -0.92
    ozyg
    -0.79
    ocaust
    -0.77
    omaly
    -0.75
    ophys
    -0.74
     pregn
    -0.73
    obe
    -0.72
    obar
    -0.71
    onyms
    -0.71
    odynam
    -0.71
    POSITIVE LOGITS
     Sanders
    1.27
    Sanders
    1.16
     Supporters
    0.91
    INTON
    0.90
    '
    0.81
     Caucus
    0.80
     delegates
    0.79
    Bernie
    0.78
     Bros
    0.77
    rade
    0.77
    Activations Density 0.008%

    No Known Activations