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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 498
    Prev
    Next
    INDEX
    Explanations

    terms related to weaponry and violence

    oai_token-act-pair · gpt-3.5-turbo

    references to snipers or sniper-related content

    oai_token-act-pair · gpt-4-turbo

    terms related to snipers and military or combat situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.88
    uce
    -0.80
    iggurat
    -0.76
    ð
    -0.75
    arenthood
    -0.73
    fect
    -0.72
    ktop
    -0.72
     Cosby
    -0.71
    inventoryQuantity
    -0.70
    isconsin
    -0.69
    POSITIVE LOGITS
     sniper
    1.22
     snipers
    1.06
     rifles
    1.00
     rifle
    0.97
     Sniper
    0.82
     Rifle
    0.77
     acad
    0.76
     bullets
    0.76
     grenade
    0.75
     trooper
    0.72
    Activations Density 0.011%

    No Known Activations