© 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. 10-RES-JB
    11. 10271
    Prev
    Next
    INDEX
    Explanations

    words related to digging or digging tools

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bur" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administ
    -0.78
    ECT
    -0.65
     Peel
    -0.64
    ovie
    -0.62
    enza
    -0.60
     Painter
    -0.60
     MFT
    -0.60
    Torrent
    -0.59
     outsourcing
    -0.58
    ICES
    -0.58
    POSITIVE LOGITS
    pees
    1.27
    rito
    1.23
    row
    1.18
    rowing
    1.15
    geon
    1.15
    liest
    1.12
    rows
    1.09
    ried
    1.07
    lap
    1.07
    bling
    1.04
    Activations Density 0.018%

    No Known Activations