© 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. 13281
    Prev
    Next
    INDEX
    Explanations

    numerical values that represent age or quantity

    oai_token-act-pair · gpt-3.5-turbo

    numerical references, particularly related to age or quantities

    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
    Bank
    -0.75
    ller
    -0.74
    Helper
    -0.71
    BOOK
    -0.70
    Climate
    -0.69
     Belief
    -0.67
    Guard
    -0.64
    aque
    -0.64
    erness
    -0.64
    KI
    -0.62
    POSITIVE LOGITS
     thousand
    1.16
    eenth
    1.01
     hundred
    1.00
    teenth
    0.89
    fold
    0.84
     thous
    0.84
    uously
    0.82
    ieth
    0.81
     Thousand
    0.80
    oreal
    0.79
    Activations Density 0.016%

    No Known Activations