© 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. 10268
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "command" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to military or authoritative commands

    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
    sung
    -0.70
    RAG
    -0.68
     Investor
    -0.65
    bley
    -0.64
    iders
    -0.64
    iate
    -0.62
     Hawking
    -0.62
    Ô
    -0.61
     Bloom
    -0.60
    ONSORED
    -0.60
    POSITIVE LOGITS
    eering
    1.39
    eers
    1.11
    eer
    1.01
    line
    1.00
    ments
    0.99
    ment
    0.94
     line
    0.91
     sender
    0.85
    aining
    0.84
    ement
    0.84
    Activations Density 0.034%

    No Known Activations