© 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. 6-RES-JB
    11. 2595
    Prev
    Next
    INDEX
    Explanations

    mentions of explosive devices like grenades

    oai_token-act-pair · gpt-3.5-turbo

    references to grenades and uranium, particularly in a military or conflict context

    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
    imus
    -1.02
    ï¸
    -1.01
    ype
    -0.99
    oof
    -0.86
    itudes
    -0.85
    Ľ
    -0.85
    icles
    -0.84
    avery
    -0.82
    pir
    -0.81
    yg
    -0.80
    POSITIVE LOGITS
     bom
    0.69
     launcher
    0.68
     mines
    0.67
     externalToEVAOnly
    0.65
     launchers
    0.64
     poppy
    0.63
     capacitor
    0.62
    schild
    0.61
     mining
    0.61
     uranium
    0.60
    Activations Density 0.082%

    No Known Activations