© 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. 20744
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals in specific scenarios or interactions

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" and its variations related to individuals in various contexts

    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
     Anything
    -0.69
     Beginning
    -0.63
     Gothic
    -0.59
     Texture
    -0.58
    å½
    -0.58
     Ending
    -0.56
     Meaning
    -0.55
     creation
    -0.55
    stop
    -0.55
     Spending
    -0.54
    POSITIVE LOGITS
    upon
    1.36
     promptly
    1.10
     subsequently
    1.06
    oping
    1.03
    oped
    1.02
     resembled
    0.97
     then
    0.97
     proceeded
    0.96
     resided
    0.96
     wished
    0.95
    Activations Density 0.176%

    No Known Activations