© 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. 9-RES-JB
    11. 7244
    Prev
    Next
    INDEX
    Explanations

    food-related words or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a" indicating new experiences or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AIDS
    -0.94
    Contents
    -0.82
     Ebola
    -0.79
    evidence
    -0.78
    âĢİ
    -0.76
    independence
    -0.74
     allegations
    -0.73
    anism
    -0.71
    vind
    -0.70
    advertising
    -0.70
    POSITIVE LOGITS
     lot
    1.39
     bunch
    1.36
     couple
    1.27
     LOT
    1.21
     few
    1.20
     nice
    1.15
     bit
    1.12
     handful
    1.04
     decent
    1.03
     little
    1.00
    Activations Density 0.502%

    No Known Activations