© 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. 12-RES-JB
    11. 2304
    Prev
    Next
    INDEX
    Explanations

    words related to surveillance and unauthorized recording of conversations or activities without consent

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to surveillance and privacy concerns

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    omore
    -0.80
     rye
    -0.71
     celebration
    -0.70
    ogie
    -0.70
     honors
    -0.69
     Frankie
    -0.69
     derby
    -0.68
     rebirth
    -0.66
     Negro
    -0.66
    cil
    -0.65
    POSITIVE LOGITS
     encryption
    1.43
     hackers
    1.41
    NSA
    1.40
     encrypted
    1.40
     malware
    1.40
     encrypt
    1.38
    encrypted
    1.35
     iCloud
    1.33
    illance
    1.31
     NSA
    1.31
    Activations Density 0.895%

    No Known Activations