© 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. 13781
    Prev
    Next
    INDEX
    Explanations

    proper nouns in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and their achievements

    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
    ã
    -0.79
    Delivery
    -0.77
    arest
    -0.69
    Applic
    -0.68
    reetings
    -0.66
    isha
    -0.66
    Commerce
    -0.65
    fts
    -0.64
    tnc
    -0.63
    Numbers
    -0.63
    POSITIVE LOGITS
     famously
    1.34
     pioneered
    1.27
     coined
    1.17
     later
    1.15
     tragically
    1.09
     spawned
    1.08
     assassinated
    1.05
     eventually
    1.04
     died
    1.04
     championed
    1.02
    Activations Density 0.431%

    No Known Activations