© 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. 9758
    Prev
    Next
    INDEX
    Explanations

    topics related to political conflicts and international relations

    oai_token-act-pair · gpt-3.5-turbo

    references to Middle Eastern countries and issues related to Muslims and immigration

    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
    åĭ
    -0.84
    ATA
    -0.78
    IFF
    -0.71
     BMC
    -0.71
     Quadro
    -0.70
     Nich
    -0.68
    rams
    -0.67
    riks
    -0.66
     Jord
    -0.66
     Jag
    -0.66
    POSITIVE LOGITS
    ghazi
    0.89
     uranium
    0.85
     plutonium
    0.78
     favorably
    0.72
     consulate
    0.72
     hoax
    0.72
    ĵĺ
    0.69
    cake
    0.69
     Uran
    0.69
    ophobic
    0.69
    Activations Density 0.195%

    No Known Activations