© 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. 8-RES-JB
    11. 19394
    Prev
    Next
    INDEX
    Explanations

    words related to seeking vengeance or retaliating

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with revenge and retaliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ographics
    -0.78
     livest
    -0.74
    umbers
    -0.73
    uddle
    -0.73
    oak
    -0.69
    ographic
    -0.68
    igel
    -0.68
    osite
    -0.67
    orage
    -0.66
    estone
    -0.66
    POSITIVE LOGITS
     retali
    1.08
     retaliation
    1.06
     retribution
    1.04
     against
    1.02
     retaliate
    1.02
     revenge
    0.96
     repr
    0.94
     vengeance
    0.89
     attacks
    0.88
     wrath
    0.87
    Activations Density 0.059%

    No Known Activations