© 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. 5211
    Prev
    Next
    INDEX
    Explanations

    news-related incidents or events involving people and actions taken against them such as arrests, injuries, or suspensions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" indicating occurrences related to events or actions

    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
     Extend
    -0.87
    isSpecialOrderable
    -0.73
    izable
    -0.70
     Countries
    -0.70
    Amount
    -0.69
     newsletters
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.68
     caveats
    -0.68
     formulas
    -0.68
     Generations
    -0.66
    POSITIVE LOGITS
     stabbed
    1.41
     murdered
    1.40
     gunned
    1.37
     assassinated
    1.34
     sentenced
    1.34
     killed
    1.33
     fined
    1.33
     arrested
    1.33
     kidnapped
    1.29
     assaulted
    1.27
    Activations Density 0.206%

    No Known Activations