© 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. 11543
    Prev
    Next
    INDEX
    Explanations

    news articles byline information, specifying authors and dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating authorship or attribution in a text

    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
     Creed
    -0.70
     Vall
    -0.70
     susp
    -0.69
     Aval
    -0.66
     trope
    -0.66
     refunds
    -0.63
     defaults
    -0.63
     Stall
    -0.63
     undercut
    -0.62
     Pledge
    -0.62
    POSITIVE LOGITS
    BBC
    1.60
    EVA
    1.05
    Associated
    1.02
    WASHINGTON
    1.02
    Bloomberg
    0.99
    Guest
    0.97
    CBS
    0.96
    Reuters
    0.96
    Narr
    0.96
    NEW
    0.95
    Activations Density 0.052%

    No Known Activations