© 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. 4-RES-JB
    11. 20776
    Prev
    Next
    INDEX
    Explanations

    the word "means" followed by a definition or explanation

    oai_token-act-pair · gpt-3.5-turbo

    definitions or meanings of concepts

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

    No Comments

    Negative Logits
    thumbnails
    -0.84
    Newsletter
    -0.68
    uner
    -0.68
    SPONSORED
    -0.68
    âĨij
    -0.66
    oked
    -0.66
    EStreamFrame
    -0.66
     prosecuted
    -0.65
    taboola
    -0.64
    ception
    -0.64
    POSITIVE LOGITS
    terday
    0.96
    hift
    0.82
     goodbye
    0.71
     spirited
    0.71
    к
    0.69
    ãĥ¼ãĥĨãĤ£
    0.63
    cules
    0.63
    los
    0.62
    lessness
    0.61
     something
    0.61
    Activations Density 0.035%

    No Known Activations