© 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. 2251
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to specific languages and their dialects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific languages and linguistic features

    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
     PB
    -0.66
     TW
    -0.65
     OCT
    -0.65
     SAN
    -0.65
    GD
    -0.65
     BU
    -0.64
     antiv
    -0.63
     WW
    -0.63
     COM
    -0.62
     DIRECT
    -0.62
    POSITIVE LOGITS
    iasis
    1.12
    aneers
    1.07
    idation
    1.07
    eers
    0.99
    adies
    0.97
    arians
    0.97
    ouses
    0.97
    acist
    0.97
    oses
    0.96
    antes
    0.96
    Activations Density 0.210%

    No Known Activations