© 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. 7-RES-JB
    11. 3146
    Prev
    Next
    INDEX
    Explanations

    references to physical altercations or fights

    oai_token-act-pair · gpt-3.5-turbo

    instances of conflict or physical confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akeru
    -0.72
    Label
    -0.71
    eele
    -0.70
     stocking
    -0.67
    engineering
    -0.63
    ãģĹ
    -0.63
     certific
    -0.62
    extra
    -0.62
    label
    -0.62
    SOURCE
    -0.62
    POSITIVE LOGITS
     ensued
    1.26
     between
    1.18
     involving
    0.91
    halla
    0.87
     brawl
    0.85
    manship
    0.85
     raged
    0.84
     amongst
    0.84
     erupted
    0.83
    between
    0.82
    Activations Density 0.195%

    No Known Activations