© 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. 4-RES-JB
    11. 17142
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and legislative actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of "Sen." followed by a senator's name

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

    No Comments

    Negative Logits
    obyl
    -0.68
    ritis
    -0.67
     underpin
    -0.67
    ologies
    -0.64
     traffickers
    -0.64
    worms
    -0.64
     mosqu
    -0.64
    zn
    -0.64
    pecially
    -0.63
    zsche
    -0.63
    POSITIVE LOGITS
     Majority
    0.88
     Olympia
    0.87
     Louie
    0.80
     Jesse
    0.75
     Candidate
    0.74
     Congressman
    0.73
     Garrison
    0.72
     Sheila
    0.72
     Cu
    0.72
     Barack
    0.72
    Activations Density 0.042%

    No Known Activations