© 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. 11-RES-JB
    11. 12981
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and accusations

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism or accusations concerning credibility and hypocrisy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.82
    cend
    -0.75
     goodbye
    -0.69
    inct
    -0.65
     unbeat
    -0.63
    soDeliveryDate
    -0.63
    capacity
    -0.62
     Governors
    -0.62
     negotiators
    -0.61
    mony
    -0.61
    POSITIVE LOGITS
     retweet
    1.43
     publish
    1.28
     misrepresent
    1.27
     plagiar
    1.26
     libel
    1.20
     dissemin
    1.16
     publishing
    1.16
     publishes
    1.16
     debunk
    1.15
     slander
    1.11
    Activations Density 0.525%

    No Known Activations