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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24442
    Prev
    Next
    INDEX
    Explanations

    words related to economic sanctions and penalties imposed on countries or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sanctions and punitive actions

    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
    ãĤ¡
    -0.98
    utenberg
    -0.73
    ItemThumbnailImage
    -0.67
    auntlet
    -0.66
    oux
    -0.66
    igree
    -0.66
    igue
    -0.66
    avascript
    -0.66
    aucuses
    -0.63
    女
    -0.63
    POSITIVE LOGITS
     viol
    1.40
     perpetrators
    1.25
     offenders
    1.23
     negligent
    1.12
     abusers
    1.07
     individuals
    1.04
     culprit
    1.01
     firms
    0.98
     traffickers
    0.98
     anyone
    0.97
    Activations Density 0.220%

    No Known Activations