© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    the word "ham" or variations of the word "hamstring"

    oai_token-act-pair · gpt-3.5-turbo

    references to "ham" and related terms, including injuries associated with "hamstring."

    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
     Debt
    -0.85
     Styles
    -0.72
    ylene
    -0.70
     Spect
    -0.70
     Merge
    -0.68
    uci
    -0.67
     Morph
    -0.66
    ocide
    -0.66
     Charges
    -0.66
     Purch
    -0.65
    POSITIVE LOGITS
     ham
    3.95
     Ham
    1.81
    Ham
    1.71
     hamstring
    1.70
     HAM
    1.60
     hob
    1.60
    ham
    1.34
     jam
    1.23
     hind
    1.22
     rabbit
    1.12
    Activations Density 0.009%

    No Known Activations