© 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. 14715
    Prev
    Next
    INDEX
    Explanations

    mentions of the passage of time and instances of repetition

    oai_token-act-pair · gpt-3.5-turbo

    references to repeated occurrences over time frames or intervals

    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
    itive
    -0.79
     GOODMAN
    -0.74
    $$$$
    -0.69
    $$
    -0.69
     Secondly
    -0.68
    ecause
    -0.67
    unts
    -0.65
     sqor
    -0.65
    =(
    -0.63
    æĺ¯
    -0.62
    POSITIVE LOGITS
     succession
    1.21
     row
    0.85
     successive
    0.74
     seven
    0.74
     five
    0.74
     six
    0.73
     consecutive
    0.73
     four
    0.73
     nine
    0.72
     less
    0.71
    Activations Density 0.052%

    No Known Activations