© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5477
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or certainty

    oai_token-act-pair · gpt-3.5-turbo

    emphatic affirmations or statements that express clarity and certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uese
    -0.83
    eport
    -0.76
    rella
    -0.76
    aily
    -0.74
    oleon
    -0.73
    ntil
    -0.70
    lite
    -0.69
    nesota
    -0.69
    enaries
    -0.69
    anish
    -0.68
    POSITIVE LOGITS
     deline
    1.00
     marked
    0.87
     identifiable
    0.85
     differentiated
    0.84
     distinguish
    0.82
     articulated
    0.77
     differentiate
    0.76
     visible
    0.76
     audible
    0.76
     belongs
    0.75
    Activations Density 0.024%

    No Known Activations