© 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. 6-RES-JB
    11. 2856
    Prev
    Next
    INDEX
    Explanations

    phrases related to seriousness or intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seriously" used to emphasize statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifully
    -0.85
    anooga
    -0.77
    tein
    -0.76
    orem
    -0.76
     Thumbnails
    -0.72
    atu
    -0.71
     Parenthood
    -0.71
    eenth
    -0.71
    ries
    -0.69
    winner
    -0.68
    POSITIVE LOGITS
     entertained
    0.79
     injure
    0.79
     retarded
    0.74
     injuring
    0.73
     considered
    0.73
     consider
    0.73
    minent
    0.72
     dent
    0.72
     considering
    0.69
    mond
    0.69
    Activations Density 0.023%

    No Known Activations