© 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. 17148
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Hans"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names

    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
    aneously
    -0.89
     IMAGES
    -0.84
     Scotia
    -0.80
    aneous
    -0.74
    otions
    -0.73
    bably
    -0.73
    cial
    -0.69
    inent
    -0.67
    WORK
    -0.67
    selves
    -0.65
    POSITIVE LOGITS
    hin
    0.95
    sein
    0.95
     Andersen
    0.89
     Hans
    0.87
    hus
    0.85
     Anders
    0.82
    iewicz
    0.81
    hu
    0.80
     Hann
    0.79
    riks
    0.75
    Activations Density 0.009%

    No Known Activations