© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11567
    Prev
    Next
    INDEX
    Explanations

    references to sports injuries and players missing games due to injuries

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with injuries and their impacts on seasons

    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
     impunity
    -0.77
     popul
    -0.65
     dens
    -0.63
     ingenious
    -0.60
     indo
    -0.60
     anecd
    -0.60
     indistinguishable
    -0.60
     timeless
    -0.58
     catchy
    -0.58
     proudly
    -0.57
    POSITIVE LOGITS
     due
    1.33
     owing
    1.08
    due
    1.05
     altogether
    1.02
     because
    0.97
     :(
    0.89
     recovering
    0.85
    because
    0.84
    Due
    0.81
    ecause
    0.80
    Activations Density 0.246%

    No Known Activations