© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15549
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "numerous."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "numerous."

    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
    atum
    -0.76
    robe
    -0.71
    heed
    -0.70
    fter
    -0.70
    iman
    -0.70
    emb
    -0.69
    bas
    -0.69
    pper
    -0.68
    obar
    -0.68
    ocene
    -0.67
    POSITIVE LOGITS
     occasions
    0.93
     iterations
    0.93
     rounds
    0.93
     occurrences
    0.91
     facets
    0.86
     times
    0.83
     instances
    0.83
     thousand
    0.83
     repet
    0.82
     hundred
    0.82
    Activations Density 0.031%

    No Known Activations