© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 19885
    Prev
    Next
    INDEX
    Explanations

    words related to retaliation and retaliatory actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to retaliation

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

    No Comments

    Negative Logits
     Dying
    -0.73
    ographics
    -0.72
    opathy
    -0.71
    verend
    -0.68
    olesterol
    -0.68
    baum
    -0.67
    âĢ¢âĢ¢
    -0.66
     Moor
    -0.65
     Matter
    -0.65
    igmat
    -0.65
    POSITIVE LOGITS
     retaliation
    1.35
     retali
    1.26
     retaliate
    1.22
     retribution
    1.05
     repr
    1.01
     punishment
    0.89
     against
    0.85
     punitive
    0.81
     deterrent
    0.81
     aggression
    0.77
    Activations Density 0.007%

    No Known Activations