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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14823
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Yes" in the context of voting or expressing agreement

    oai_token-act-pair · gpt-3.5-turbo

    affirmations related to voting

    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
     destro
    -0.65
    ULAR
    -0.63
     resemb
    -0.62
     externalToEVAOnly
    -0.61
    bage
    -0.60
     restricted
    -0.60
    worn
    -0.60
    perial
    -0.59
     isolated
    -0.59
    jri
    -0.59
    POSITIVE LOGITS
    terday
    1.19
    ï¸
    0.91
     vote
    0.89
    yes
    0.83
    YES
    0.82
    aye
    0.80
     votes
    0.80
     Means
    0.78
     Vote
    0.77
    vation
    0.77
    Activations Density 0.068%

    No Known Activations