© 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. 12549
    Prev
    Next
    INDEX
    Explanations

    verbs expressing desire or intention

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or longing

    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
    ilings
    -0.68
    oven
    -0.64
    usting
    -0.59
    à¼
    -0.58
     ®
    -0.58
    è¦ļéĨĴ
    -0.58
    washer
    -0.57
    NVIDIA
    -0.57
    cedented
    -0.56
    bug
    -0.55
    POSITIVE LOGITS
     to
    1.17
     revenge
    0.96
     something
    0.94
     nothing
    0.81
     answers
    0.79
    only
    0.78
     assurances
    0.78
     permission
    0.78
     someone
    0.77
     vengeance
    0.77
    Activations Density 0.131%

    No Known Activations