© 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. 22271
    Prev
    Next
    INDEX
    Explanations

    information related to the release of movies and TV shows on Blu-ray Disc

    oai_token-act-pair · gpt-3.5-turbo

    references to Blu-ray discs and their releases

    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
     TODAY
    -0.68
     IST
    -0.66
     improv
    -0.65
     Democr
    -0.63
     Gallup
    -0.63
     unwelcome
    -0.63
     idiosyncr
    -0.62
     Arkansas
    -0.61
     WW
    -0.61
    @@@@
    -0.60
    POSITIVE LOGITS
    ray
    1.61
    Ray
    1.38
    rays
    1.37
    RAY
    1.04
    disc
    0.89
    Rated
    0.89
    cellent
    0.88
    ROM
    0.88
    duct
    0.87
    Disk
    0.86
    Activations Density 0.023%

    No Known Activations