© 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. 6-RES-JB
    11. 12779
    Prev
    Next
    INDEX
    Explanations

    specific numeric durations representing time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TextColor
    -0.77
     scissors
    -0.61
     Appropri
    -0.61
     envy
    -0.61
     Seraph
    -0.60
     sparing
    -0.60
     Machina
    -0.60
     savior
    -0.59
    cipled
    -0.57
     skepticism
    -0.57
    POSITIVE LOGITS
    th
    0.91
    %.
    0.87
     months
    0.83
    %:
    0.79
     iterations
    0.79
    %"
    0.79
     acres
    0.78
     years
    0.78
    orks
    0.77
    %,
    0.77
    Activations Density 0.091%

    No Known Activations