© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23800
    Prev
    Next
    INDEX
    Explanations

    terms related to political nominations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "nomination."

    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
    hed
    -0.78
    chie
    -0.75
    working
    -0.71
    jer
    -0.71
     Extrem
    -0.68
    ells
    -0.67
    inav
    -0.65
    Org
    -0.65
    hing
    -0.65
    gm
    -0.65
    POSITIVE LOGITS
     nomination
    1.14
     nominations
    1.09
     nominate
    1.04
     nominees
    0.97
     ballots
    0.95
     nominated
    0.93
     nominating
    0.93
     ballot
    0.90
     candidacy
    0.87
     candidate
    0.83
    Activations Density 0.010%

    No Known Activations