© 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. 2555
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding or programming

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boilerplate."

    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
     antiquity
    -0.75
     places
    -0.63
     pills
    -0.60
     Enlightenment
    -0.60
     Ay
    -0.59
     tribes
    -0.59
     Quartz
    -0.58
     funer
    -0.58
     hikes
    -0.57
     Bronze
    -0.57
    POSITIVE LOGITS
    iler
    4.73
    ilers
    3.93
    iling
    2.11
    iled
    1.93
    iles
    1.54
    ile
    1.54
    ilings
    1.44
    iller
    1.42
    ilation
    1.38
    ils
    1.26
    Activations Density 0.010%

    No Known Activations