© 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. 4494
    Prev
    Next
    INDEX
    Explanations

    verbs related to violent or harmful actions

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

    words and phrases associated with violence and 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
    Þ
    -1.44
    PDATE
    -1.43
     behavi
    -1.33
     exting
    -1.25
    ß
    -1.23
    ãĥ¼ãĥĨ
    -1.23
     corrid
    -1.19
     millenn
    -1.16
     referen
    -1.12
     conclud
    -1.12
    POSITIVE LOGITS
    ache
    0.91
    ary
    0.91
    ical
    0.91
    aled
    0.90
    aged
    0.90
    hire
    0.90
    atal
    0.90
    orial
    0.89
    agically
    0.89
    ate
    0.88
    Activations Density 0.402%

    No Known Activations