© 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. 20882
    Prev
    Next
    INDEX
    Explanations

    the word "mean" used as a connector in sentences indicating logical contrast or clarification

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that doesn't mean" used to introduce a contrasting point or clarification

    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
    EStreamFrame
    -0.72
    ortment
    -0.71
    hani
    -0.69
    Sources
    -0.69
    cart
    -0.68
     largeDownload
    -0.67
    iets
    -0.66
    wine
    -0.66
    taboola
    -0.66
    court
    -0.65
    POSITIVE LOGITS
     anymore
    0.94
     anything
    0.87
    terday
    0.86
    erest
    0.81
     necessarily
    0.77
     anybody
    0.72
     bother
    0.70
     disrespect
    0.69
     goodbye
    0.69
     exactly
    0.68
    Activations Density 0.021%

    No Known Activations