© 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. 1-RES-JB
    11. 20428
    Prev
    Next
    INDEX
    Explanations

    references to hackers and their activities

    oai_token-act-pair · gpt-3.5-turbo

    references to hackers and hacking activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Towns
    -0.77
     Baal
    -0.74
    âĢ¢âĢ¢
    -0.73
    zl
    -0.73
     Loving
    -0.73
    ã
    -0.69
     Leban
    -0.66
     Blessing
    -0.66
    ++++++++++++++++
    -0.65
     Pillar
    -0.65
    POSITIVE LOGITS
     hackers
    1.31
     hacker
    1.25
     hacking
    1.03
    intosh
    0.91
    paces
    0.89
    ileaks
    0.85
    hack
    0.84
     nerds
    0.84
     glitch
    0.83
     hack
    0.83
    Activations Density 0.006%

    No Known Activations