© 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. 22090
    Prev
    Next
    INDEX
    Explanations

    phrases related to a significant degree or scale of something

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate significant magnitude or scale

    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
    arters
    -0.83
    wich
    -0.77
    hner
    -0.74
    sburgh
    -0.74
    tein
    -0.72
    nce
    -0.72
     Sut
    -0.71
    rament
    -0.70
     Harbor
    -0.69
    oslov
    -0.69
    POSITIVE LOGITS
    Introduced
    0.79
     multiplayer
    0.72
     amounts
    0.70
     subsid
    0.70
    rolet
    0.68
    ilitary
    0.68
     funded
    0.68
     strapped
    0.67
     massively
    0.66
     accelerated
    0.66
    Activations Density 0.022%

    No Known Activations