© 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. 12-RES-JB
    11. 4820
    Prev
    Next
    INDEX
    Explanations

    controversial events or scandals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of controversy or scandal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ij士
    -0.65
    ordinate
    -0.64
     worldly
    -0.61
     adject
    -0.59
    é¾įå
    -0.58
     athletic
    -0.56
    姫
    -0.56
     Orient
    -0.55
     temperament
    -0.55
     ageing
    -0.55
    POSITIVE LOGITS
     fiasco
    1.06
     debacle
    1.04
     saga
    0.96
     plag
    0.89
     rumor
    0.86
    iasco
    0.83
    undrum
    0.83
     controversy
    0.83
     hoax
    0.81
     epidemic
    0.79
    Activations Density 0.408%

    No Known Activations