© 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. 3-RES-JB
    11. 1898
    Prev
    Next
    INDEX
    Explanations

    words related to bats

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bat."

    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
    ãĥ´ãĤ¡
    -0.73
    FINE
    -0.70
    xia
    -0.68
    ISTORY
    -0.68
    phis
    -0.66
    zanne
    -0.65
    mber
    -0.64
    éĸ
    -0.63
    perse
    -0.62
    Ô
    -0.62
    POSITIVE LOGITS
    bat
    0.92
     bat
    0.86
    tered
    0.81
    bats
    0.75
    ista
    0.75
    manship
    0.74
    rooms
    0.72
    oche
    0.72
    computer
    0.71
    oto
    0.71
    Activations Density 0.005%

    No Known Activations