© 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. 4-RES-JB
    11. 22238
    Prev
    Next
    INDEX
    Explanations

    instances of the word "an"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "an."

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

    No Comments

    Negative Logits
    BLE
    -0.74
     scares
    -0.72
     Peg
    -0.72
     psychiat
    -0.71
    byss
    -0.68
    BOOK
    -0.67
    ï¸
    -0.67
     Regions
    -0.63
     Wid
    -0.63
    âĸº
    -0.63
    POSITIVE LOGITS
    abolic
    1.12
    agram
    1.10
    onym
    1.09
    omal
    1.07
    ointed
    1.03
    onymous
    0.95
    alogue
    0.94
    notation
    0.91
    esthetic
    0.91
    omaly
    0.90
    Activations Density 0.261%

    No Known Activations