© 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. 11-RES-JB
    11. 12709
    Prev
    Next
    INDEX
    Explanations

    words related to overcoming obstacles or surpassing limits

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "break" and its various forms

    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
     Oops
    -0.69
     Detail
    -0.64
    ctive
    -0.61
    eers
    -0.59
    eton
    -0.57
    geries
    -0.57
    trak
    -0.56
    risome
    -0.55
    expr
    -0.55
    anza
    -0.54
    POSITIVE LOGITS
    red
    1.09
    neck
    0.98
    through
    0.94
     ranks
    0.88
     apart
    0.86
     stereotypes
    0.85
     ties
    0.83
     hearts
    0.82
    owship
    0.79
     bread
    0.79
    Activations Density 0.041%

    No Known Activations