© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 18797
    Prev
    Next
    INDEX
    Explanations

    the name "Elle" with varying levels of certainty with higher activations indicating stronger certainty

    oai_token-act-pair · gpt-3.5-turbo

    the word "elle" and its various forms or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eminent
    -0.67
    izoph
    -0.63
     archaic
    -0.62
     imperative
    -0.61
     manifest
    -0.61
     critical
    -0.60
     logical
    -0.60
     prevailing
    -0.59
    raviolet
    -0.59
     DPR
    -0.59
    POSITIVE LOGITS
    elle
    1.11
    tto
    1.06
    lette
    0.92
    tti
    0.91
    anne
    0.91
    ttes
    0.88
    tta
    0.84
    izabeth
    0.84
    llo
    0.83
    cules
    0.82
    Activations Density 0.008%

    No Known Activations