© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18562
    Prev
    Next
    INDEX
    Explanations

    the word "Hillary"

    oai_token-act-pair · gpt-3.5-turbo

    references to Hillary Clinton

    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
    dash
    -0.69
    outer
    -0.69
    isode
    -0.68
    isu
    -0.67
    igm
    -0.67
    ribune
    -0.67
    ORPG
    -0.63
    âķIJ
    -0.63
    iple
    -0.63
    0200
    -0.63
    POSITIVE LOGITS
     Rodham
    2.00
     Clinton
    1.83
    Clinton
    1.48
     Clintons
    1.40
    clinton
    1.17
    INTON
    1.16
     Hillary
    1.09
    ileaks
    1.00
     Sanders
    0.96
    Hillary
    0.94
    Activations Density 0.023%

    No Known Activations