© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 13840
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Comm" or variations thereof in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Commission."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.89
     hinge
    -0.80
     Sora
    -0.79
     tilt
    -0.77
    lations
    -0.75
    loop
    -0.70
     ultrasound
    -0.69
     silicone
    -0.68
    apy
    -0.68
     shrink
    -0.68
    POSITIVE LOGITS
     Comm
    3.79
    Comm
    2.33
     COMM
    1.80
    comm
    1.53
     comm
    1.48
     Commission
    1.24
     Com
    1.24
     Committee
    1.23
     commodities
    1.18
     Committees
    1.18
    Activations Density 0.023%

    No Known Activations