© 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. 8-RES-JB
    11. 3323
    Prev
    Next
    INDEX
    Explanations

    words related to seizing or taking control of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seize" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lich
    -0.71
    appa
    -0.70
     offic
    -0.65
    gnu
    -0.64
    study
    -0.63
    govtrack
    -0.62
     preferring
    -0.61
     opting
    -0.60
    die
    -0.60
     Serving
    -0.60
    POSITIVE LOGITS
     control
    0.97
     possession
    0.95
     advantage
    0.83
     Raqqa
    0.82
     refuge
    0.80
     custody
    0.75
     CONTROL
    0.75
     Control
    0.74
     hold
    0.72
     victory
    0.70
    Activations Density 0.074%

    No Known Activations