© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    nonprofit organizations that advocate for various causes

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or groups that advocate for social justice or human rights

    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
    Grade
    -0.70
     guessing
    -0.69
     spoiled
    -0.67
    Luck
    -0.66
    grain
    -0.66
    tale
    -0.65
     drying
    -0.65
     chewing
    -0.64
     Royale
    -0.63
     Conan
    -0.62
    POSITIVE LOGITS
     organize
    1.25
     promotes
    1.22
     campaigned
    1.18
     opposes
    1.18
     lobbied
    1.14
     advocated
    1.14
     organized
    1.13
     advocates
    1.12
     endorsed
    1.09
     lobb
    1.08
    Activations Density 0.356%

    No Known Activations