© 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. 4729
    Prev
    Next
    INDEX
    Explanations

    words related to violent or aggressive acts

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

    contexts involving violence or aggression

    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
    HCR
    -0.89
    WAYS
    -0.87
    sbm
    -0.87
    forestation
    -0.81
    thood
    -0.81
    Ô
    -0.75
    issions
    -0.75
    inery
    -0.75
    amar
    -0.74
    isan
    -0.74
    POSITIVE LOGITS
     railing
    1.15
     ceiling
    1.12
     intruder
    1.07
     unconscious
    1.06
     camera
    1.04
     offending
    1.04
     corpse
    1.01
     assailant
    1.01
     lifeless
    1.01
     unsuspecting
    1.00
    Activations Density 0.244%

    No Known Activations