© 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. 8-RES-JB
    6. 15033
    Prev
    Next
    INDEX
    Explanations

    names of people ending in 'aine'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "aine" and other similar suffixes or variations

    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
    nets
    -0.91
    een
    -0.89
    orie
    -0.88
    imon
    -0.88
    mallow
    -0.88
    okin
    -0.87
    heast
    -0.85
    creen
    -0.82
    heastern
    -0.80
    hered
    -0.80
    POSITIVE LOGITS
    issance
    1.27
     Vista
    0.68
     Theft
    0.68
     Archdemon
    0.66
     Gomez
    0.65
     Herrera
    0.65
     theft
    0.64
    quez
    0.64
     Rape
    0.64
     Lans
    0.63
    Activations Density 0.118%

    No Known Activations