© 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. 8-RES-JB
    11. 14145
    Prev
    Next
    INDEX
    Explanations

    words related to deception or cleverness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trick" or related variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ccording
    -0.69
     isot
    -0.67
     Expend
    -0.65
     enrichment
    -0.64
     Domain
    -0.63
    Interstitial
    -0.61
     Hemp
    -0.60
    college
    -0.60
     concess
    -0.59
    Found
    -0.59
    POSITIVE LOGITS
    ery
    1.42
    ster
    1.20
    eries
    1.15
    sters
    1.09
    aroo
    1.01
    iest
    1.01
    ulic
    0.96
    door
    0.96
     tricks
    0.94
    oggle
    0.94
    Activations Density 0.039%

    No Known Activations