© 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. 11-RES-JB
    11. 22268
    Prev
    Next
    INDEX
    Explanations

    references to official government departments and positions

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental and intelligence agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captcha
    -0.83
    estamp
    -0.65
     glim
    -0.64
     pel
    -0.63
     landsl
    -0.63
     favourite
    -0.62
     wax
    -0.62
     refere
    -0.62
     graz
    -0.62
     trem
    -0.62
    POSITIVE LOGITS
     Programs
    0.90
    intelligence
    0.88
     Intelligence
    0.86
    ghazi
    0.84
    assad
    0.83
     Directorate
    0.82
    secret
    0.82
    elligence
    0.81
     Investigations
    0.81
    CLASSIFIED
    0.80
    Activations Density 0.163%

    No Known Activations