© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or interaction

    oai_token-act-pair · gpt-3.5-turbo
    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
    idav
    -0.78
     Gould
    -0.64
    possibly
    -0.62
     grasped
    -0.61
     grasp
    -0.60
    oÄŁ
    -0.60
     grasping
    -0.59
     Conclusion
    -0.58
     Expand
    -0.58
     Continued
    -0.58
    POSITIVE LOGITS
     regularly
    1.40
     daily
    1.23
     yearly
    1.21
     weekly
    1.18
     nightly
    1.15
     occasionally
    1.13
     frequently
    1.13
     constantly
    1.11
     everyday
    1.08
     periodically
    1.08
    Activations Density 0.744%

    No Known Activations