© 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. 16137
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or progression

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time in various contexts

    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
     wonder
    -0.53
    irie
    -0.53
    FOR
    -0.52
     retro
    -0.51
     prevail
    -0.50
     helicop
    -0.50
     urgently
    -0.49
     Breed
    -0.49
    Reviewed
    -0.48
     corpor
    -0.48
    POSITIVE LOGITS
     of
    0.97
     thereof
    0.85
    course
    0.80
     course
    0.79
    ebin
    0.78
    Course
    0.66
    anian
    0.66
    uncture
    0.66
    ainer
    0.66
    Of
    0.65
    Activations Density 0.035%

    No Known Activations