Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16017
    Prev
    Next
    INDEX
    Explanations

    instances of retaliation and retaliatory actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to retaliation and punitive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ographics
    -0.73
     Matter
    -0.72
    opathy
    -0.71
    scape
    -0.69
     Dying
    -0.67
    igmat
    -0.66
    oto
    -0.65
     ç¥ŀ
    -0.65
    verend
    -0.64
    leaf
    -0.63
    POSITIVE LOGITS
     retaliation
    1.36
     retali
    1.31
     retaliate
    1.27
     repr
    1.12
     retribution
    1.09
     against
    0.99
     wrath
    0.93
     punitive
    0.84
     attacks
    0.81
     punishment
    0.81
    Activations Density 0.020%

    No Known Activations