© 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. 8534
    Prev
    Next
    INDEX
    Explanations

    phrases representing comparison, evaluation, or connection

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that contain structural or comparative elements

    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
    ãĤ´ãĥ³
    -0.74
    -,
    -0.72
    ãĥ¥
    -0.69
    cellaneous
    -0.68
    ļéĨĴ
    -0.67
    ////////////////
    -0.67
    Includes
    -0.65
    OTHER
    -0.64
    ,...
    -0.64
    Winged
    -0.63
    POSITIVE LOGITS
     however
    1.33
     though
    1.17
     it
    0.96
     although
    0.88
     therefore
    0.86
     there
    0.84
     we
    0.83
     this
    0.81
     moreover
    0.78
     they
    0.78
    Activations Density 0.263%

    No Known Activations