© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20421
    Prev
    Next
    INDEX
    Explanations

    terms related to establishments or organizations

    oai_token-act-pair · gpt-3.5-turbo

    different forms of the word "entertain" and its variants

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

    No Comments

    Negative Logits
     brightly
    -0.74
     Mehran
    -0.69
     favour
    -0.67
    jri
    -0.66
     honour
    -0.62
     illuminated
    -0.62
     retard
    -0.61
     mirrors
    -0.61
     insensitive
    -0.61
     linen
    -0.60
    POSITIVE LOGITS
     Lauder
    0.88
    cheon
    0.79
    tainment
    0.76
    ogo
    0.75
    ById
    0.74
    prise
    0.73
    lement
    0.72
    ENE
    0.70
    mere
    0.70
    isu
    0.70
    Activations Density 0.079%

    No Known Activations