© 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. 1-RES-JB
    11. 20355
    Prev
    Next
    INDEX
    Explanations

    specific indexes or rankings mentioned in texts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various indices and the term "Index."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.70
    selves
    -0.69
    llular
    -0.69
    pter
    -0.63
    nature
    -0.62
    tein
    -0.62
    tek
    -0.62
    azer
    -0.62
    pton
    -0.62
     damn
    -0.61
    POSITIVE LOGITS
     Index
    1.25
    Index
    0.95
    eers
    0.79
    heimer
    0.78
     index
    0.78
     Rating
    0.76
     Contents
    0.75
     indexes
    0.74
     List
    0.72
     Coverage
    0.72
    Activations Density 0.004%

    No Known Activations