© 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. 8-RES-JB
    11. 12458
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "blatant"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blatant" and related descriptors indicating egregious behavior or misconduct

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    agine
    -0.86
    meric
    -0.82
    rieve
    -0.81
    yip
    -0.80
    iership
    -0.76
    astery
    -0.75
    asio
    -0.74
    ovember
    -0.74
    ulton
    -0.72
    joy
    -0.72
    POSITIVE LOGITS
     misrepresent
    1.19
     disregard
    1.16
     hypocrisy
    1.15
     plagiar
    1.10
     violations
    0.99
     corruption
    0.97
     fals
    0.95
     injustice
    0.95
     mishand
    0.95
     offenders
    0.95
    Activations Density 0.147%

    No Known Activations