© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21223
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or fixations, particularly the word "obsessed."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obsession and fascination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī
    -0.64
     detrim
    -0.64
    soDeliveryDate
    -0.61
    hands
    -0.59
    inventoryQuantity
    -0.57
    nl
    -0.57
     commencement
    -0.57
     actu
    -0.56
     dissenting
    -0.56
     coercion
    -0.56
    POSITIVE LOGITS
     withd
    0.85
     with
    0.85
     fascinated
    0.80
     With
    0.77
    atically
    0.73
     WITH
    0.73
    with
    0.72
     obsessed
    0.69
    ishly
    0.69
    oling
    0.69
    Activations Density 0.091%

    No Known Activations