© 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. 10-RES-JB
    11. 3065
    Prev
    Next
    INDEX
    Explanations

    numeric sequences in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.76
    assetsadobe
    -0.75
    LY
    -0.71
    ingly
    -0.69
    heit
    -0.68
    âĢİ
    -0.68
    Allows
    -0.67
    plete
    -0.67
    ledge
    -0.66
    soType
    -0.66
    POSITIVE LOGITS
     aforementioned
    1.35
    ses
    1.05
     dozen
    1.01
     four
    0.98
     foregoing
    0.96
     three
    0.94
     twelve
    0.94
     nine
    0.94
     eleven
    0.93
     five
    0.91
    Activations Density 0.129%

    No Known Activations