© 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. 5759
    Prev
    Next
    INDEX
    Explanations

    actors and their roles in movies and TV shows

    oai_token-act-pair · gpt-3.5-turbo

    references to actors and their roles in films or television

    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
     VIDEOS
    -0.94
    wcs
    -0.82
    Statistics
    -0.79
    RELATED
    -0.79
    Recent
    -0.76
    Notice
    -0.74
    iform
    -0.72
    pour
    -0.72
    Frames
    -0.71
    akings
    -0.71
    POSITIVE LOGITS
     Agent
    1.11
     Detective
    1.01
     narrator
    0.97
     Colonel
    0.96
     protagonist
    0.96
     villain
    0.93
     Captain
    0.93
     Sheriff
    0.93
     Lucius
    0.93
     Peggy
    0.93
    Activations Density 0.100%

    No Known Activations