© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 7504
    Prev
    Next
    INDEX
    Explanations

    words related to communication and interaction

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "clip" and other similar phonetic patterns

    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
     NCT
    -0.84
     Benz
    -0.71
     Bourbon
    -0.68
    minecraft
    -0.68
     Flan
    -0.68
     Willow
    -0.67
     Saban
    -0.67
     Fior
    -0.64
     Fernand
    -0.63
     Jinn
    -0.62
    POSITIVE LOGITS
    cled
    1.25
    cling
    1.02
    uration
    0.97
    rency
    0.96
    rocal
    0.95
    oration
    0.94
    ctions
    0.94
    brance
    0.90
    urated
    0.85
    struction
    0.84
    Activations Density 0.084%

    No Known Activations