© 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. 0-RES-JB
    11. 11785
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "Sham"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sham" and related terms

    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
    etus
    -0.82
    20439
    -0.80
     von
    -0.72
    wagen
    -0.70
     Garn
    -0.67
    XX
    -0.67
     Chrys
    -0.65
     constraints
    -0.64
    rolet
    -0.64
    IX
    -0.63
    POSITIVE LOGITS
     Sham
    3.94
    Sham
    3.22
     sham
    2.83
     Shaman
    1.82
     shaman
    1.58
     Nim
    1.21
     Kab
    1.19
     Raz
    1.10
     Abram
    1.04
     Uri
    0.97
    Activations Density 0.019%

    No Known Activations