© 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 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. 10-RES-JB
    11. 3443
    Prev
    Next
    INDEX
    Explanations

    phrases related to violence and aggression

    oai_token-act-pair · gpt-3.5-turbo

    references to war or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.89
    atown
    -0.71
    ruary
    -0.70
    ĸļ
    -0.69
    cribed
    -0.69
     Volunte
    -0.68
    ISTORY
    -0.67
    olkien
    -0.66
    anship
    -0.65
    zed
    -0.65
    POSITIVE LOGITS
     crap
    1.16
     entire
    1.12
     messenger
    1.09
     offending
    1.06
     throats
    1.01
     intruder
    1.01
     opponent
    1.00
     unsuspecting
    0.97
     innocent
    0.94
     enemy
    0.93
    Activations Density 0.266%

    No Known Activations