© 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. 9-RES-JB
    11. 11263
    Prev
    Next
    INDEX
    Explanations

    text related to the prefix "lam"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lam" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.70
     Morales
    -0.67
    hani
    -0.60
     shortest
    -0.58
    ee
    -0.58
     Owl
    -0.57
    XT
    -0.57
     strawberries
    -0.56
     maintenance
    -0.56
     longest
    -0.56
    POSITIVE LOGITS
    borgh
    1.29
    ydia
    1.25
    ming
    1.21
    mer
    1.09
    ingo
    1.03
    beer
    0.98
     Dunk
    0.95
    ento
    0.95
    orous
    0.94
    gdala
    0.94
    Activations Density 0.056%

    No Known Activations