© 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. 3-RES-JB
    11. 1899
    Prev
    Next
    INDEX
    Explanations

    phrases related to making claims or accusations

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-conventional text markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emale
    -0.52
     afterwards
    -0.52
    ornings
    -0.51
    chuk
    -0.51
    *.
    -0.50
    ée
    -0.49
    worth
    -0.48
    rade
    -0.48
     alas
    -0.48
    arettes
    -0.48
    POSITIVE LOGITS
     same
    0.96
     aforementioned
    0.83
     latest
    0.82
     latter
    0.81
    ses
    0.76
     following
    0.75
     simplest
    0.75
     hottest
    0.73
     fastest
    0.73
     largest
    0.73
    Activations Density 1.169%

    No Known Activations