© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    references to specific items or concepts within longer texts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various processes and concepts in discussions, particularly those involving quality, policies, and regulatory aspects

    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
    thood
    -0.62
    ilaterally
    -0.56
    cale
    -0.55
    vae
    -0.55
    ornia
    -0.54
     Flavoring
    -0.54
     Lanka
    -0.52
    merce
    -0.51
    outube
    -0.51
    azeera
    -0.50
    POSITIVE LOGITS
     itself
    0.75
    iest
    0.70
     succeeded
    0.65
     consisted
    0.65
    ultimate
    0.64
     lasted
    0.60
     portion
    0.60
     consists
    0.58
     revolves
    0.58
     operator
    0.57
    Activations Density 0.759%

    No Known Activations