© 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. 11177
    Prev
    Next
    INDEX
    Explanations

    mentions of political and news-related events

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events

    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
    imum
    -0.64
    cffffcc
    -0.63
    Abstract
    -0.63
    Sov
    -0.62
    ãĤ´
    -0.60
     iod
    -0.59
    RNA
    -0.59
     envis
    -0.58
     invention
    -0.58
    irements
    -0.57
    POSITIVE LOGITS
     tweeted
    1.22
     retweet
    1.09
     tweeting
    1.07
     tweets
    0.98
     Twitter
    0.97
     tweet
    0.96
     spokesperson
    0.94
     twitter
    0.94
     meanwhile
    0.92
     TMZ
    0.88
    Activations Density 1.019%

    No Known Activations