© 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. 8-RES-JB
    11. 7066
    Prev
    Next
    INDEX
    Explanations

    words related to the name "El."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific proper nouns and character names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llor
    -0.72
     IMAGES
    -0.68
    okemon
    -0.64
     breast
    -0.63
    minecraft
    -0.62
     REUTERS
    -0.61
    Downloadha
    -0.60
    iversal
    -0.60
    mong
    -0.59
     senseless
    -0.58
    POSITIVE LOGITS
    abeth
    1.00
    abet
    0.79
    otte
    0.78
     guiActiveUn
    0.76
    ande
    0.73
    ée
    0.72
     Musk
    0.71
    WHERE
    0.70
    apo
    0.67
    onde
    0.67
    Activations Density 0.099%

    No Known Activations