© 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. 7-RES-JB
    11. 21137
    Prev
    Next
    INDEX
    Explanations

    movie-related terms and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to films and movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.81
    NetMessage
    -0.76
     Dhabi
    -0.71
    cale
    -0.69
    ktop
    -0.69
    ession
    -0.68
    conservancy
    -0.67
    unte
    -0.67
    ystem
    -0.66
    ²¾
    -0.66
    POSITIVE LOGITS
     premiered
    1.15
     itself
    1.03
    runner
    0.88
    wright
    0.85
    runners
    0.82
    writer
    0.81
    writers
    0.81
     airs
    0.81
     theat
    0.80
     revolves
    0.80
    Activations Density 0.194%

    No Known Activations