© 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 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. 9787
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sk" followed by a number, particularly focusing on instances where the number is high (9 or 10)

    oai_token-act-pair · gpt-3.5-turbo

    words related to skiing or activities related to it

    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
    interstitial
    -0.79
     Haram
    -0.79
    oyer
    -0.72
     Barrett
    -0.72
    amiya
    -0.69
    iott
    -0.69
    Corn
    -0.68
    âĻ¦
    -0.66
    ensing
    -0.65
     Lucius
    -0.65
    POSITIVE LOGITS
     sk
    3.67
     skating
    1.97
     Sk
    1.90
     skate
    1.84
    sk
    1.84
    Sk
    1.83
     ski
    1.54
     skiing
    1.47
     SK
    1.39
     skim
    1.32
    Activations Density 0.015%

    No Known Activations