© 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. 2-RES-JB
    11. 17237
    Prev
    Next
    INDEX
    Explanations

    instances of the word "erk" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "werk" and its variations as it relates to a specific topic or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CPC
    -0.66
    lder
    -0.63
     mes
    -0.63
     vested
    -0.63
    ------------------------------------------------
    -0.62
     Duc
    -0.61
     cru
    -0.59
     Marijuana
    -0.58
     Gravity
    -0.58
     Wilkinson
    -0.57
    POSITIVE LOGITS
    erk
    1.31
    owitz
    1.02
    wagen
    1.01
    hof
    0.95
    erker
    0.88
    rand
    0.88
    lein
    0.87
    manship
    0.87
    ers
    0.84
    lass
    0.83
    Activations Density 0.007%

    No Known Activations