© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10710
    Prev
    Next
    INDEX
    Explanations

    instances of the word "doubt"

    oai_token-act-pair · gpt-3.5-turbo

    phrases conveying certainty or lack of doubt

    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
    emetery
    -0.81
    ahime
    -0.72
     neighb
    -0.70
    eatures
    -0.70
    aeus
    -0.68
    ells
    -0.68
    nect
    -0.67
    aeper
    -0.67
    aml
    -0.65
     intest
    -0.64
    POSITIVE LOGITS
     whatsoever
    0.95
    worthiness
    0.89
    lessly
    0.87
    fulness
    0.76
    worthy
    0.70
    fully
    0.69
     respecting
    0.68
     ORIG
    0.66
     unanswered
    0.65
     underest
    0.63
    Activations Density 0.010%

    No Known Activations