© 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. 20828
    Prev
    Next
    INDEX
    Explanations

    numerical sequences likely referring to some coding or identification system

    oai_token-act-pair · gpt-3.5-turbo

    numerical references or codes related to various classifications or levels of danger and administrative processes

    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
    agna
    -0.77
    retch
    -0.72
     whim
    -0.59
     Hallow
    -0.58
     Tanz
    -0.58
    enegger
    -0.58
    inventoryQuantity
    -0.58
     rushed
    -0.57
     helpless
    -0.57
     Eat
    -0.57
    POSITIVE LOGITS
    xual
    0.92
    FY
    0.84
    +,
    0.81
    nces
    0.81
    Gs
    0.77
    Bs
    0.75
    E
    0.72
    Cs
    0.72
    HB
    0.71
    DM
    0.71
    Activations Density 0.055%

    No Known Activations