© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10172
    Prev
    Next
    INDEX
    Explanations

    dates and times in the format "00:00"

    oai_token-act-pair · gpt-3.5-turbo

    sequences of time markers or timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
     aggreg
    -0.67
     gut
    -0.66
    hus
    -0.64
     aggregation
    -0.63
    nar
    -0.62
     moderation
    -0.61
    antle
    -0.61
     Pit
    -0.61
    odan
    -0.59
     Gul
    -0.59
    POSITIVE LOGITS
     00
    3.63
     01
    2.21
     02
    1.91
     0000
    1.85
     000
    1.84
     04
    1.79
     03
    1.78
     05
    1.72
     06
    1.64
     07
    1.62
    Activations Density 0.023%

    No Known Activations