© 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. 18614
    Prev
    Next
    INDEX
    Explanations

    people or characters studying or having studied various subjects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "studying" and its variations in different contexts

    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
    adjusted
    -0.82
    appointed
    -0.79
    ãĥ¼ãĥ³
    -0.74
    leased
    -0.71
    onda
    -0.70
    prone
    -0.69
    posted
    -0.68
    closure
    -0.68
    riott
    -0.68
    warning
    -0.68
    POSITIVE LOGITS
     abroad
    1.11
     biology
    0.97
     psychology
    0.95
     sociology
    0.94
     medicine
    0.92
     anthropology
    0.92
     physics
    0.90
    english
    0.89
     algebra
    0.89
     Biology
    0.88
    Activations Density 0.049%

    No Known Activations