© 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. 10-RES-JB
    11. 16130
    Prev
    Next
    INDEX
    Explanations

    reports on news or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reports" indicating news or journalism activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istical
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    agues
    -0.59
    respective
    -0.58
     gauge
    -0.57
    folk
    -0.56
    lor
    -0.56
    thumbnails
    -0.55
     Ples
    -0.55
    lling
    -0.54
    POSITIVE LOGITS
     below
    0.68
     BELOW
    0.67
    :[
    0.66
    :
    0.65
    :(
    0.64
    :"
    0.64
    :'
    0.62
    olate
    0.62
    :#
    0.60
     NAD
    0.60
    Activations Density 0.103%

    No Known Activations