© 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. 4-RES-JB
    11. 16479
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly the word "hundred"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hundred."

    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
    kamp
    -0.71
    rang
    -0.69
    beh
    -0.67
    obal
    -0.66
    akers
    -0.60
     Noir
    -0.60
    vals
    -0.60
    hra
    -0.59
    felt
    -0.59
    MAC
    -0.59
    POSITIVE LOGITS
     thousand
    1.23
    ousand
    1.06
     Thousand
    1.02
    undred
    0.95
    eenth
    0.89
     fifty
    0.85
     dollars
    0.84
    uously
    0.83
     milliseconds
    0.83
     thous
    0.83
    Activations Density 0.013%

    No Known Activations