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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 10580
    Prev
    Next
    INDEX
    Explanations

    people who have become famous or taken on significant roles in various fields

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "became."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inately
    -0.75
    ramid
    -0.72
    oning
    -0.72
    inarily
    -0.69
    alian
    -0.67
    orneys
    -0.65
    enger
    -0.65
    orney
    -0.62
    been
    -0.62
    hov
    -0.61
    POSITIVE LOGITS
     accustomed
    0.98
     embroiled
    0.97
     extinct
    0.91
     entangled
    0.90
     acquainted
    0.89
     aware
    0.88
     disillusion
    0.85
    oslav
    0.82
     obsessed
    0.81
     ens
    0.76
    Activations Density 0.045%

    No Known Activations