© 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. 3-RES-JB
    11. 8967
    Prev
    Next
    INDEX
    Explanations

    mentions related to specific regions or groups in relation to military or political activities

    oai_token-act-pair · gpt-3.5-turbo

    specific references to groups or entities associated with conflict or military activity

    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
     Wonderland
    -0.81
     Minotaur
    -0.73
     Piercing
    -0.72
     USAF
    -0.67
     Virgin
    -0.67
    ++++++++++++++++
    -0.67
     Detective
    -0.67
     Purg
    -0.66
     Detect
    -0.66
     Addiction
    -0.66
    POSITIVE LOGITS
     Houth
    0.87
    accompan
    0.85
    eni
    0.84
    enei
    0.83
    ilitation
    0.81
    isi
    0.81
    arov
    0.78
    awi
    0.78
    ileaks
    0.78
     dissidents
    0.77
    Activations Density 0.004%

    No Known Activations