© 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. 20463
    Prev
    Next
    INDEX
    Explanations

    words related to tampering or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    references to tampering or manipulation

    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
    Nap
    -0.77
    Footnote
    -0.73
     Colo
    -0.68
    æĥ
    -0.68
     Jacket
    -0.66
     RIS
    -0.65
     Sketch
    -0.63
    ģ«
    -0.63
    XP
    -0.62
     Kinnikuman
    -0.62
    POSITIVE LOGITS
    ammed
    1.41
    eco
    0.95
    asus
    0.90
    onite
    0.85
    vertising
    0.81
    amia
    0.81
    entary
    0.81
    lehem
    0.79
     cram
    0.78
    ulhu
    0.76
    Activations Density 0.004%

    No Known Activations