© 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. 11-RES-JB
    6. 22443
    Prev
    Next
    INDEX
    Explanations

    phrases connecting one thing to a larger group or category, often emphasizing the diversity or quantity of examples

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating examples or instances

    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
    same
    -0.87
    ioned
    -0.75
    alos
    -0.70
    cffff
    -0.69
    iol
    -0.67
    then
    -0.66
    nob
    -0.65
    awaru
    -0.64
    never
    -0.64
    shared
    -0.64
    POSITIVE LOGITS
     examples
    1.07
     example
    1.01
     scratching
    1.01
     sampling
    0.98
     iceberg
    0.90
     sample
    0.90
     illustration
    0.86
     symptom
    0.86
     glimpse
    0.82
     anecdotal
    0.82
    Activations Density 0.129%

    No Known Activations