© 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. 1-RES-JB
    11. 14420
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual named "Reince Priebus" who holds various positions within the Republican National Committee

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, Reince Priebus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shows
    -0.76
    gom
    -0.75
    icycle
    -0.70
    iamond
    -0.68
     Cluster
    -0.67
    psc
    -0.65
    fare
    -0.65
    ç¥ŀ
    -0.64
     Globe
    -0.64
    certain
    -0.64
    POSITIVE LOGITS
     Priebus
    1.33
    cffff
    0.94
    kefeller
    0.83
    aukee
    0.80
    afort
    0.77
    utenant
    0.70
    ptive
    0.68
    dinand
    0.68
    etti
    0.67
    rament
    0.67
    Activations Density 0.008%

    No Known Activations