© 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. 3-RES-JB
    6. 3031
    Prev
    Next
    INDEX
    Explanations

    keywords related to circuit boards and electronic hardware

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "board" in various contexts

    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
    olon
    -0.73
    igham
    -0.71
    bered
    -0.67
     Hoover
    -0.67
    ankind
    -0.66
     plural
    -0.66
    icity
    -0.65
    selves
    -0.65
     wills
    -0.63
    rir
    -0.63
    POSITIVE LOGITS
    board
    1.23
    walk
    1.19
    wal
    1.02
    Board
    0.99
    meal
    0.98
    ridges
    0.94
    gaming
    0.93
    boarding
    0.92
    boards
    0.92
    wright
    0.89
    Activations Density 0.019%

    No Known Activations