© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 709
    Prev
    Next
    INDEX
    Explanations

    names or terms related to terrorist groups such as Al-Qaeda

    oai_token-act-pair · gpt-3.5-turbo

    references to Al-Qaeda

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.77
     AVG
    -0.71
     Dickinson
    -0.67
    ulhu
    -0.66
    DragonMagazine
    -0.65
     Unicorn
    -0.65
     CG
    -0.65
     Sponsor
    -0.64
     cringe
    -0.63
     CES
    -0.63
    POSITIVE LOGITS
    tra
    1.07
    bay
    1.03
    affiliated
    1.03
    backed
    1.01
    based
    0.99
    area
    0.98
    shaped
    0.97
    su
    0.96
    Qaida
    0.95
    Qaeda
    0.94
    Activations Density 0.130%

    No Known Activations