© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4-RES-JB
    11. 10715
    Prev
    Next
    INDEX
    Explanations

    phrases related to food or ingredients, especially cheese

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "mo" in different contexts

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

    No Comments

    Negative Logits
    ĪĴ
    -1.11
     prelim
    -0.72
    COMPLE
    -0.69
     subp
    -0.64
     HDL
    -0.61
    handedly
    -0.60
    displayText
    -0.60
     habitual
    -0.60
    blogspot
    -0.58
    ©¶æ
    -0.58
    POSITIVE LOGITS
    uddin
    0.86
    gow
    0.81
    opot
    0.77
    ensen
    0.77
    lein
    0.76
    enne
    0.74
    itary
    0.72
    htar
    0.70
    iter
    0.69
    adh
    0.69
    Activations Density 0.102%

    No Known Activations