© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17035
    Prev
    Next
    INDEX
    Explanations

    words related to management roles and hierarchical positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to management and generalizations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     quar
    -0.65
     poles
    -0.64
     bom
    -0.62
     Palest
    -0.62
     lime
    -0.61
     seams
    -0.61
     tunnels
    -0.60
     tubing
    -0.60
     cones
    -0.60
     linen
    -0.58
    POSITIVE LOGITS
    #$
    0.91
    gage
    0.74
    ATIONS
    0.73
    rx
    0.68
    atoes
    0.68
    estyles
    0.68
    qua
    0.67
    iple
    0.66
    requency
    0.66
    LEASE
    0.65
    Activations Density 0.080%

    No Known Activations