Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 18210
    Prev
    Next
    INDEX
    Explanations

    references to the name "Diane" with varying activations for different spellings and its association with certain contexts such as sports, crime, and corporate services

    oai_token-act-pair · gpt-3.5-turbo

    names or references to individuals or characters

    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
    rador
    -0.81
    s
    -0.80
    enance
    -0.78
     Carbuncle
    -0.76
    achusetts
    -0.75
    enegger
    -0.71
    ernaut
    -0.70
    iosity
    -0.70
    awaru
    -0.70
     Seym
    -0.69
    POSITIVE LOGITS
    gas
    1.00
    jad
    0.91
    IRO
    0.81
    ffe
    0.81
    hyde
    0.80
    cia
    0.78
    vil
    0.77
    venue
    0.76
    quin
    0.75
    utenant
    0.74
    Activations Density 0.044%

    No Known Activations