© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2222
    Prev
    Next
    INDEX
    Explanations

    strong emphasis on specific phrases starting with "The"

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-informative segments in the text

    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
     beforehand
    -0.63
    omever
    -0.63
    thood
    -0.62
    ÏĢ
    -0.62
    *.
    -0.58
    Ò
    -0.58
    !.
    -0.58
     alongside
    -0.57
     with
    -0.57
     without
    -0.56
    POSITIVE LOGITS
    oret
    1.14
    resa
    1.09
    odore
    1.06
    ories
    0.84
    nce
    0.79
     latter
    0.79
     oldest
    0.78
    atre
    0.77
     Economist
    0.75
     biggest
    0.75
    Activations Density 0.502%

    No Known Activations