© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19074
    Prev
    Next
    INDEX
    Explanations

    mentions of warnings, threats, and alerts in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating warnings and associated threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.78
     sacrament
    -0.75
    fuck
    -0.74
    Favorite
    -0.72
     Therapy
    -0.66
    Film
    -0.66
    otti
    -0.65
    OTUS
    -0.64
    ographed
    -0.63
    Hon
    -0.62
    POSITIVE LOGITS
     shortages
    1.51
     worsening
    1.37
     fears
    1.28
     difficulties
    1.24
     sluggish
    1.22
     dwindling
    1.22
     deteriorating
    1.20
     widespread
    1.20
     delays
    1.20
     uncertainties
    1.19
    Activations Density 0.370%

    No Known Activations