© 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. 12406
    Prev
    Next
    INDEX
    Explanations

    the word "wild" appearing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "build."

    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
    SOURCE
    -0.85
    perature
    -0.72
    MIT
    -0.72
    displayText
    -0.70
    kins
    -0.68
    earchers
    -0.68
    andise
    -0.65
    PLAY
    -0.64
    Jen
    -0.63
    CHR
    -0.63
    POSITIVE LOGITS
    ild
    1.04
    erers
    0.78
    sburg
    0.77
    rag
    0.76
    er
    0.75
    sson
    0.75
    ness
    0.75
    reth
    0.74
    itudinal
    0.74
    rance
    0.73
    Activations Density 0.007%

    No Known Activations