© 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. 0-RES-JB
    11. 4925
    Prev
    Next
    INDEX
    Explanations

    keywords related to data collection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Collect" and related terms indicating aggregation or collection

    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
    Not in Any Lists

    No Comments

    Negative Logits
    debian
    -0.91
    Bug
    -0.69
     Buddy
    -0.69
     Sabha
    -0.68
    packages
    -0.67
    achy
    -0.67
    Bir
    -0.67
    eros
    -0.67
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    ¥µ
    -0.66
    POSITIVE LOGITS
     Collect
    2.20
     Sons
    1.78
    Collect
    1.49
    collect
    1.30
     Farrell
    1.29
     CW
    1.27
    )(
    1.25
     Phelps
    0.98
     PD
    0.96
     Huntington
    0.90
    Activations Density 0.049%

    No Known Activations