© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 3905
    Prev
    Next
    INDEX
    Explanations

    words related to strategies, methods, or plans

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "approach."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pite
    -0.77
     istg
    -0.72
    cake
    -0.72
    ongo
    -0.70
    arus
    -0.67
    ukes
    -0.63
    bleacher
    -0.62
    gin
    -0.61
    ãĥ©ãĥ³
    -0.61
    rake
    -0.60
    POSITIVE LOGITS
     approach
    0.96
     Approach
    0.90
    ison
    0.81
    isons
    0.76
     approaches
    0.75
    idon
    0.74
    perty
    0.74
    yip
    0.73
    ISON
    0.73
    aphael
    0.72
    Activations Density 0.019%

    No Known Activations