© 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. 8-RES-JB
    11. 14970
    Prev
    Next
    INDEX
    Explanations

    plural gerunds related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases associated with actions or events, particularly those that involve "pl" followed by specific letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.81
    PRES
    -0.74
    NEY
    -0.72
    Madison
    -0.72
    lish
    -0.70
    âĸ¬
    -0.70
    gerald
    -0.69
    VICE
    -0.69
    LY
    -0.68
    BOOK
    -0.65
    POSITIVE LOGITS
    aques
    1.21
    atter
    1.21
    umber
    1.18
    umbers
    1.15
    umb
    1.11
    iers
    1.10
    acer
    1.08
    acent
    1.08
    ump
    1.08
    umm
    1.05
    Activations Density 0.013%

    No Known Activations