© 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. 12-RES-JB
    11. 3579
    Prev
    Next
    INDEX
    Explanations

    the keyword "mod" or its variations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "mod" and its variations, indicating a focus on modifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.64
     Mata
    -0.58
    holding
    -0.57
     Bulldogs
    -0.56
     damning
    -0.56
     monarchy
    -0.56
     paraph
    -0.55
     shorth
    -0.54
    nces
    -0.54
     begging
    -0.54
    POSITIVE LOGITS
    elled
    1.48
    ulo
    1.34
    ded
    1.29
    ular
    1.28
    icum
    1.28
    ding
    1.28
    ulus
    1.28
    ules
    1.27
    elling
    1.26
    eller
    1.26
    Activations Density 0.025%

    No Known Activations