© 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. 6-RES-JB
    11. 9334
    Prev
    Next
    INDEX
    Explanations

    words related to negative connotations or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the term "ill" paired with various contexts suggesting negativity or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.80
    EStream
    -0.78
    ļéĨĴ
    -0.77
    £ı
    -0.75
    EStreamFrame
    -0.75
    uyomi
    -0.74
     compr
    -0.69
    kefeller
    -0.68
    theless
    -0.68
    ©¶æ¥µ
    -0.66
    POSITIVE LOGITS
    uminati
    1.44
    inois
    1.24
    ogical
    1.16
    iberal
    1.16
    umin
    1.15
    awar
    1.13
    icit
    1.07
    usive
    1.03
    nesses
    1.00
    igan
    0.99
    Activations Density 0.016%

    No Known Activations