© 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. 10-RES-JB
    11. 6099
    Prev
    Next
    INDEX
    Explanations

    instances where the number "two" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "two."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thouse
    -0.75
    ablishment
    -0.73
    annel
    -0.72
    ICLE
    -0.72
    gerald
    -0.71
     Caption
    -0.70
    zyme
    -0.69
    ifice
    -0.68
    urden
    -0.67
    ook
    -0.67
    POSITIVE LOGITS
     thirds
    1.94
     halves
    1.38
     dozen
    1.20
     weeks
    1.19
    nd
    1.11
     tablespoons
    1.06
     sides
    1.04
     hundred
    1.04
    fold
    1.02
    thirds
    0.99
    Activations Density 0.122%

    No Known Activations