© 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. 920
    Prev
    Next
    INDEX
    Explanations

    numerical values like dates, percentages, measurements, and financial figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and specific identifiers, particularly related to individuals or organizations

    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
    manship
    -0.73
    natureconservancy
    -0.66
    ĵĺ
    -0.65
     Tradable
    -0.59
    hement
    -0.59
     ACTIONS
    -0.55
    itiveness
    -0.55
    terness
    -0.52
    uristic
    -0.51
    hemy
    -0.51
    POSITIVE LOGITS
    ĸļ
    0.72
    pora
    0.70
     womb
    0.64
    hyde
    0.63
     umb
    0.51
     ponds
    0.51
    restricted
    0.51
    anca
    0.50
    thia
    0.49
    near
    0.49
    Activations Density 1.393%

    No Known Activations