© 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. 11-RES-JB
    11. 4773
    Prev
    Next
    INDEX
    Explanations

    efficient methods or solutions, particularly in terms of communication, transportation, and resource management

    oai_token-act-pair · gpt-3.5-turbo

    themes related to efficiency and effective communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    older
    -0.91
    enium
    -0.73
    clair
    -0.72
    assis
    -0.71
    atches
    -0.69
    ingle
    -0.69
    irements
    -0.68
    itten
    -0.67
    idium
    -0.66
    gements
    -0.66
    POSITIVE LOGITS
     means
    1.75
     method
    1.69
     methods
    1.61
     avenue
    1.59
     ways
    1.57
     way
    1.54
     avenues
    1.52
     route
    1.39
     recourse
    1.36
     mechanism
    1.33
    Activations Density 0.556%

    No Known Activations