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

    Neuronpedia

    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. 8-RES-JB
    11. 20492
    Prev
    Next
    INDEX
    Explanations

    locations within news articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the comma punctuation mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.69
    natureconservancy
    -0.67
    epad
    -0.67
    thood
    -0.67
    ttp
    -0.66
    ernel
    -0.64
    ught
    -0.62
    bsite
    -0.60
    agine
    -0.59
    ole
    -0.59
    POSITIVE LOGITS
     CITY
    1.00
     Calif
    0.87
     COUNTY
    0.85
     INC
    0.84
     JUL
    0.83
     MEN
    0.81
     PRES
    0.80
    INC
    0.80
    VILLE
    0.79
     COL
    0.78
    Activations Density 0.032%

    No Known Activations