© 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. 0-RES-JB
    11. 15434
    Prev
    Next
    INDEX
    Explanations

    news outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leve
    -0.71
     ambient
    -0.68
     pass
    -0.66
     skill
    -0.66
     fitting
    -0.65
     armor
    -0.64
     score
    -0.64
     worn
    -0.63
     quint
    -0.63
     Elys
    -0.62
    POSITIVE LOGITS
    News
    3.83
     News
    2.25
    news
    2.22
    NEWS
    2.21
     NEWS
    1.90
     news
    1.66
    Politics
    1.47
    Magazine
    1.46
    Journal
    1.38
    Rum
    1.30
    Activations Density 0.008%

    No Known Activations