© 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. 11-RES-JB
    11. 7643
    Prev
    Next
    INDEX
    Explanations

    phrases related to dangerous or violent activities

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving accidents or violent altercations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    osponsors
    -1.00
    notes
    -0.74
     guides
    -0.73
    esters
    -0.72
     trophies
    -0.72
     RELE
    -0.71
     relics
    -0.69
     graduates
    -0.69
     orphans
    -0.69
    pieces
    -0.69
    POSITIVE LOGITS
     altercation
    1.43
     robbery
    1.27
     confrontation
    1.26
     brawl
    1.22
     dispute
    1.19
     shootout
    1.19
     quarrel
    1.14
     botched
    1.14
     burglary
    1.13
     drunken
    1.10
    Activations Density 0.190%

    No Known Activations