© 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. 10-RES-JB
    11. 18769
    Prev
    Next
    INDEX
    Explanations

    titles of movies and TV shows

    oai_token-act-pair · gpt-3.5-turbo

    titles of television shows and movies

    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
     affili
    -0.68
     credibility
    -0.67
     mitigation
    -0.65
     parity
    -0.65
     restrictive
    -0.63
     subdiv
    -0.63
     accommodation
    -0.63
     contention
    -0.63
     livelihood
    -0.63
     turb
    -0.62
    POSITIVE LOGITS
     Awakens
    1.06
     Bride
    0.98
     Avenger
    0.93
     Adventures
    0.93
     Below
    0.92
     Trilogy
    0.90
     Incident
    0.88
     Chronicles
    0.87
     Difference
    0.87
     Files
    0.87
    Activations Density 0.174%

    No Known Activations