© 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. 10-RES-JB
    11. 18638
    Prev
    Next
    INDEX
    Explanations

    words related to competitions or contests

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "race."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.69
    urers
    -0.69
    oca
    -0.67
    arial
    -0.67
    azaki
    -0.65
    olia
    -0.65
    etheless
    -0.63
    ricular
    -0.63
    azy
    -0.63
    orescent
    -0.62
    POSITIVE LOGITS
    course
    1.44
    horse
    1.34
    cars
    1.09
    car
    1.04
    bike
    0.89
    mma
    0.84
    ways
    0.81
    manship
    0.80
    runner
    0.78
    nell
    0.78
    Activations Density 0.025%

    No Known Activations