© 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 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. 16654
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names related to brands, movies, or places

    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
    ";
    -0.56
    SPONSORED
    -0.56
     ______
    -0.54
     ��������
    -0.52
     Shutterstock
    -0.51
    advertisement
    -0.51
    )",
    -0.51
     behalf
    -0.49
    .....
    -0.49
    .):
    -0.49
    POSITIVE LOGITS
     assures
    0.92
     has
    0.92
     insists
    0.91
     hasn
    0.90
     agrees
    0.90
     believes
    0.90
     knows
    0.89
     intends
    0.88
     recommends
    0.88
     expects
    0.86
    Activations Density 0.694%

    No Known Activations