© 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 EvalsExportsinterp-engineNEWAPI 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. 2746
    Prev
    Next
    INDEX
    Explanations

    instances of the word "referendum."

    oai_token-act-pair · gpt-3.5-turbo

    references to referendums

    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
    DragonMagazine
    -0.85
    ienne
    -0.78
    mson
    -0.76
    ukong
    -0.74
    paces
    -0.71
    ahime
    -0.71
    bilt
    -0.70
    Enhanced
    -0.69
    iak
    -0.68
    eye
    -0.67
    POSITIVE LOGITS
     referendum
    1.23
     vote
    1.10
    ndum
    1.08
     ballot
    1.00
     result
    0.98
     votes
    0.92
     turnout
    0.90
     ballots
    0.89
     campaign
    0.89
     refere
    0.85
    Activations Density 0.045%

    No Known Activations