© 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. 19211
    Prev
    Next
    INDEX
    Explanations

    words related to distillation and brewing

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "distill" and its variations

    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
     competition
    -0.63
    Beta
    -0.62
     beta
    -0.62
     Trilogy
    -0.61
     relative
    -0.60
    bum
    -0.59
     stre
    -0.59
     stray
    -0.59
     epile
    -0.59
     unic
    -0.59
    POSITIVE LOGITS
    illing
    4.39
    illed
    2.93
    ills
    2.38
    iller
    2.28
    ILL
    1.97
    ill
    1.87
    illation
    1.59
    illery
    1.48
    illin
    1.43
    ille
    1.33
    Activations Density 0.009%

    No Known Activations