© 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. 20514
    Prev
    Next
    INDEX
    Explanations

    phrases related to security breaches or compromises

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "compromised" in various contexts

    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
    gat
    -0.81
    att
    -0.70
    uay
    -0.70
    uf
    -0.69
    Ļ
    -0.68
    Mart
    -0.68
    inker
    -0.67
    ann
    -0.66
    soon
    -0.65
    batch
    -0.65
    POSITIVE LOGITS
     compromised
    1.43
     compromising
    1.09
     comprom
    1.07
    romising
    0.97
     compromises
    0.93
     adolesc
    0.87
     compromise
    0.86
     Seym
    0.85
     undermin
    0.83
     corrupted
    0.80
    Activations Density 0.007%

    No Known Activations