© 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. 1848
    Prev
    Next
    INDEX
    Explanations

    words related to television dramas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drama in various contexts

    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
    ovo
    -0.87
    achev
    -0.74
    ossier
    -0.72
    ibel
    -0.71
    olphin
    -0.70
    erers
    -0.70
    enhagen
    -0.67
    ogether
    -0.67
    itude
    -0.67
    imus
    -0.66
    POSITIVE LOGITS
     queens
    1.02
     drama
    0.90
     queen
    0.85
     dramas
    0.85
     unfold
    0.83
     unfolds
    0.80
     theater
    0.78
     airs
    0.77
     comed
    0.75
     actor
    0.75
    Activations Density 0.033%

    No Known Activations