© 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. 3-RES-JB
    6. 9674
    Prev
    Next
    INDEX
    Explanations

    specific times and dates

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly related to time and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.73
    addle
    -0.62
    tin
    -0.61
    rike
    -0.61
    stad
    -0.60
    fork
    -0.60
    spr
    -0.60
    URI
    -0.59
    asta
    -0.58
    attribute
    -0.57
    POSITIVE LOGITS
     Colt
    0.66
    bourg
    0.63
    ĸļ
    0.63
     Porn
    0.63
    taboola
    0.62
     deduction
    0.62
    dden
    0.62
    LEASE
    0.62
    owicz
    0.62
    minster
    0.59
    Activations Density 0.645%

    No Known Activations