© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1788
    Prev
    Next
    INDEX
    Explanations

    lines of code with specific mathematical operations and syntax

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming and technical code structures

    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
    guide
    -0.72
    FontSize
    -0.72
    ellar
    -0.72
    assic
    -0.71
    ocene
    -0.71
    today
    -0.70
    avers
    -0.67
     conveyed
    -0.67
    edged
    -0.67
    76561
    -0.67
    POSITIVE LOGITS
     fn
    0.85
     Âł Âł
    0.84
     Âł Âł Âł Âł
    0.83
     {
    0.81
    olean
    0.80
     __
    0.76
     vec
    0.73
     [[
    0.72
     Vector
    0.72
     rand
    0.72
    Activations Density 0.076%

    No Known Activations