© 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. 10-RES-JB
    11. 10104
    Prev
    Next
    INDEX
    Explanations

    actions related to vandalism and violence

    oai_token-act-pair · gpt-3.5-turbo

    actions associated with violent protests and public disturbances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venture
    -0.80
    DragonMagazine
    -0.75
    ãĤ´ãĥ³
    -0.72
    Adapt
    -0.69
     redes
    -0.67
    igmat
    -0.67
    isSpecialOrderable
    -0.66
    natureconservancy
    -0.66
    cession
    -0.66
     reinvest
    -0.65
    POSITIVE LOGITS
     tyres
    1.07
     explosives
    0.99
     barric
    0.99
     tires
    0.91
     throats
    0.89
     furniture
    0.88
     bottles
    0.87
     grenades
    0.87
     rocks
    0.84
     knives
    0.84
    Activations Density 0.187%

    No Known Activations