© 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. 10712
    Prev
    Next
    INDEX
    Explanations

    numeric values, especially in fractions and decimals

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical information

    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
    .[
    -0.74
     respectively
    -0.73
    )).
    -0.71
    .''
    -0.67
    ).
    -0.66
    .).
    -0.64
     therein
    -0.64
    .
    -0.64
    ."
    -0.63
    .''.
    -0.62
    POSITIVE LOGITS
    adic
    0.70
    iple
    0.67
    phal
    0.63
    ourning
    0.62
    vous
    0.61
    cept
    0.61
    esc
    0.59
    athe
    0.59
    aves
    0.58
    ential
    0.58
    Activations Density 1.508%

    No Known Activations