© 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 EvalsExportsinterp-engineNEWAPI 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. 5572
    Prev
    Next
    INDEX
    Explanations

    mentions of militant groups such as ISIL and Hezbollah

    oai_token-act-pair · gpt-3.5-turbo

    mentions of terrorist organizations and related military entities

    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
    cock
    -0.87
    atur
    -0.79
    bell
    -0.75
    hot
    -0.73
    mond
    -0.73
    uns
    -0.73
     Niet
    -0.72
    pring
    -0.72
    print
    -0.71
    bags
    -0.70
    POSITIVE LOGITS
     ISIL
    0.74
    ovo
    0.70
    rative
    0.69
     plotting
    0.69
     encro
    0.68
    MAP
    0.67
    aukee
    0.66
     inhibition
    0.66
     Daesh
    0.64
     clearance
    0.63
    Activations Density 0.020%

    No Known Activations