© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12553
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "ours"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific term or keyword repetitively throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clarkson
    -0.68
     Metatron
    -0.64
     booth
    -0.62
     background
    -0.59
     EFF
    -0.59
     machine
    -0.58
     button
    -0.57
    xon
    -0.57
     Newton
    -0.57
     âĸł
    -0.56
    POSITIVE LOGITS
    hip
    1.22
    urs
    1.11
    uits
    1.09
    uit
    1.08
    ury
    1.06
    geons
    0.97
    atile
    0.97
    ensical
    0.95
    cript
    0.94
    rences
    0.93
    Activations Density 0.007%

    No Known Activations