© 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. 11-RES-JB
    11. 8345
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and organizations mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of important public figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -1.02
    SPONSORED
    -1.02
    '';
    -0.78
     Tsukuyomi
    -0.77
    Advertisement
    -0.72
     anyways
    -0.67
    };
    -0.65
     };
    -0.65
    âĨij
    -0.65
    ';
    -0.64
    POSITIVE LOGITS
     has
    1.03
     believes
    0.87
     wants
    0.83
     says
    0.82
     warns
    0.80
     intends
    0.79
     denies
    0.79
     alleges
    0.78
     accuses
    0.76
     may
    0.75
    Activations Density 0.269%

    No Known Activations