© 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. 0-RES-JB
    6. 7778
    Prev
    Next
    INDEX
    Explanations

    instances of the word "t" being mentioned, which could potentially represent an abbreviation or specific term related to the context

    oai_token-act-pair · gpt-3.5-turbo

    the contraction "don't."

    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
     mascul
    -0.56
     domestically
    -0.54
     unnecessarily
    -0.52
     disclaimer
    -0.51
     vulnerable
    -0.51
     closest
    -0.51
     desk
    -0.51
     permitted
    -0.50
     disqualified
    -0.50
     firsthand
    -0.50
    POSITIVE LOGITS
    t
    3.50
    tin
    1.92
    ti
    1.87
    tan
    1.83
    tal
    1.75
    tz
    1.72
    tu
    1.70
    ts
    1.70
    tk
    1.69
    tif
    1.68
    Activations Density 0.136%

    No Known Activations