© 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. 9-RES-JB
    11. 15914
    Prev
    Next
    INDEX
    Explanations

    film titles and director names

    oai_token-act-pair · gpt-3.5-turbo

    references to film directors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.84
     glim
    -0.76
    esty
    -0.67
     brut
    -0.67
    ertodd
    -0.66
    aturdays
    -0.66
    utenberg
    -0.66
    ogle
    -0.66
    DragonMagazine
    -0.66
     blasp
    -0.65
    POSITIVE LOGITS
     Netherlands
    1.40
     Philippines
    1.33
     Belgium
    1.29
     Mexico
    1.23
     France
    1.23
     Switzerland
    1.23
     Poland
    1.22
     Germany
    1.21
     Hungary
    1.21
     Pennsylvania
    1.20
    Activations Density 0.176%

    No Known Activations