© 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. 12-RES-JB
    11. 4161
    Prev
    Next
    INDEX
    Explanations

    words related to criminal incidents and violent actions

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

    descriptions of unusual or threatening events

    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
    osponsors
    -0.90
    =-=-=-=-
    -0.85
    tests
    -0.79
    olerance
    -0.79
    ographies
    -0.78
    iaries
    -0.78
    ournals
    -0.77
     moderates
    -0.77
    arters
    -0.77
    onyms
    -0.76
    POSITIVE LOGITS
     gust
    1.28
     earthquake
    1.23
     explosion
    1.22
     tornado
    1.22
     bolt
    1.18
     fireball
    1.15
     quake
    1.15
     projectile
    1.11
     breeze
    1.10
     assailant
    1.10
    Activations Density 0.326%

    No Known Activations