© 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. 4-RES-JB
    11. 16260
    Prev
    Next
    INDEX
    Explanations

    references to specific political and military groups and actions, such as the Houthi rebels and AQ (presumably Al-Qaeda)

    oai_token-act-pair · gpt-3.5-turbo

    references to specific militant groups and their activities

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

    No Comments

    Negative Logits
     Wonderland
    -0.81
     Minotaur
    -0.74
     Piercing
    -0.72
    ãĤ´ãĥ³
    -0.68
     USAF
    -0.68
     Detect
    -0.66
     Matter
    -0.66
     Archangel
    -0.65
     Edison
    -0.65
     Purg
    -0.64
    POSITIVE LOGITS
    eni
    0.90
     Houth
    0.84
    ilit
    0.82
    accompan
    0.82
    enei
    0.78
    ilitation
    0.78
    ites
    0.78
    awi
    0.77
    allowed
    0.76
    isi
    0.75
    Activations Density 0.005%

    No Known Activations