© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9490
    Prev
    Next
    INDEX
    Explanations

    words related to events or locations, especially those involving panels, races, and meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to events, locations, and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decay
    -0.60
    untled
    -0.58
     meanwhile
    -0.55
    aez
    -0.55
    idious
    -0.54
    ":[{"
    -0.54
     genuinely
    -0.53
     disappearing
    -0.52
    acca
    -0.52
     brakes
    -0.52
    POSITIVE LOGITS
     Awards
    0.60
     guiActiveUnfocused
    0.58
     semif
    0.56
     era
    0.55
     Historic
    0.55
     campus
    0.54
     plaza
    0.53
    election
    0.52
     Campus
    0.51
     Tropical
    0.51
    Activations Density 1.376%

    No Known Activations