© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17316
    Prev
    Next
    INDEX
    Explanations

    the word "dozen"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dozen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hra
    -0.76
    bro
    -0.75
    ainer
    -0.72
    usher
    -0.70
    estine
    -0.69
    liv
    -0.68
    arist
    -0.67
    claimed
    -0.67
    acus
    -0.67
    otto
    -0.65
    POSITIVE LOGITS
     thousand
    1.05
     dozen
    0.96
     Thousand
    0.96
    uously
    0.94
    uous
    0.91
     consecutive
    0.89
    acity
    0.89
     hundred
    0.83
     iterations
    0.82
    aciously
    0.80
    Activations Density 0.029%

    No Known Activations