© 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. 11-RES-JB
    6. 7586
    Prev
    Next
    INDEX
    Explanations

    occupations or roles within a community

    oai_token-act-pair · gpt-3.5-turbo

    specific roles or titles associated with individuals and professions

    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
    Sources
    -0.77
     Horses
    -0.76
    ources
    -0.74
    engers
    -0.72
    ories
    -0.72
    earchers
    -0.69
    results
    -0.69
    Users
    -0.68
    rams
    -0.68
    Contents
    -0.66
    POSITIVE LOGITS
    's
    1.31
     who
    1.13
     whom
    0.96
     whose
    0.94
    stration
    0.88
    who
    0.87
     named
    0.87
     sighting
    0.83
     haircut
    0.83
     uprising
    0.80
    Activations Density 0.333%

    No Known Activations