© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7172
    Prev
    Next
    INDEX
    Explanations

    phrases related to implementing changes or initiatives

    oai_token-act-pair · gpt-3.5-turbo
    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
    Evil
    -0.78
    lus
    -0.73
    Fuck
    -0.69
     Zionist
    -0.69
     hatred
    -0.68
     Rupert
    -0.67
     Rebellion
    -0.65
     Evil
    -0.65
     treason
    -0.65
    Appearances
    -0.64
    POSITIVE LOGITS
     prioritize
    0.96
     inspected
    0.94
     instituted
    0.93
     audits
    0.93
     redesigned
    0.92
     evaluated
    0.92
     phased
    0.92
     backlog
    0.91
     reimb
    0.91
     inspect
    0.90
    Activations Density 0.460%

    No Known Activations