© 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. 10-RES-JB
    11. 13922
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific procedures or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of formal protocols and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stocks
    -0.73
    oppable
    -0.73
    ãĥ´
    -0.73
    cart
    -0.73
    rill
    -0.72
    inese
    -0.71
    jri
    -0.69
    north
    -0.68
    kids
    -0.65
    gets
    -0.65
    POSITIVE LOGITS
     procedures
    1.01
     procedure
    1.00
     governing
    0.90
     whereby
    0.84
     instituted
    0.83
     Procedures
    0.83
     Procedure
    0.83
     protocols
    0.80
     involving
    0.79
     droid
    0.78
    Activations Density 0.091%

    No Known Activations