© 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. 2483
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights violations, war crimes, and atrocities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to violence and suffering experienced by children in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ħĭ
    -0.78
    ãĤ¦ãĤ¹
    -0.78
    isSpecialOrderable
    -0.70
     Majesty
    -0.68
     Chair
    -0.67
    AAA
    -0.67
     Awesome
    -0.66
    essment
    -0.66
    retty
    -0.64
    sense
    -0.64
    POSITIVE LOGITS
     slaughtered
    1.36
     deported
    1.36
     starved
    1.32
     murdered
    1.31
     tortured
    1.30
     starve
    1.26
     enslaved
    1.25
     raped
    1.25
     traff
    1.25
     starving
    1.25
    Activations Density 0.378%

    No Known Activations