© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6261
    Prev
    Next
    INDEX
    Explanations

    words related to various specific topics, such as photography, technology, health, and musical tastes

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated lists or phrases

    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
    ');
    -0.78
    ");
    -0.70
    vale
    -0.68
    liest
    -0.63
    maxwell
    -0.62
    ema
    -0.60
    %%
    -0.59
    ").
    -0.59
    Reply
    -0.59
    =#
    -0.59
    POSITIVE LOGITS
     coupled
    1.39
     meanwhile
    1.25
     combined
    1.21
     moreover
    1.19
     however
    1.10
     especially
    1.04
     namely
    1.03
     along
    1.00
     regardless
    0.99
     particularly
    0.99
    Activations Density 0.288%

    No Known Activations