© 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. 610
    Prev
    Next
    INDEX
    Explanations

    keywords related to incomplete or unfinished tasks or projects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incompleteness or delays in progress

    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
    ysis
    -0.90
    uge
    -0.89
    inen
    -0.86
    ocard
    -0.82
    leans
    -0.82
    upe
    -0.82
    isin
    -0.81
    inery
    -0.80
    azar
    -0.80
    anism
    -0.79
    POSITIVE LOGITS
     revolving
    0.75
     snowball
    0.68
     spaghetti
    0.68
     Kens
    0.66
     autos
    0.65
     Resolution
    0.65
     Sega
    0.63
    ãĥĩãĤ£
    0.63
     Koen
    0.62
     Western
    0.62
    Activations Density 0.034%

    No Known Activations