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. 4-RES-JB
    6. 8249
    Prev
    Next
    INDEX
    Explanations

    the word "buck" and variations of it, such as "bucks" and "buckled"

    oai_token-act-pair · gpt-3.5-turbo

    references to money or financial transactions

    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
     redistributed
    -0.62
    istically
    -0.62
    prototype
    -0.62
    20439
    -0.61
    ochemical
    -0.60
     Hiroshima
    -0.60
    effects
    -0.59
     Oslo
    -0.59
     srf
    -0.58
     Scope
    -0.57
    POSITIVE LOGITS
    whe
    1.03
     buck
    0.99
    ety
    0.93
    robe
    0.86
    die
    0.86
    tails
    0.85
    aroo
    0.82
    ed
    0.82
    enstein
    0.79
    buck
    0.79
    Activations Density 0.006%

    No Known Activations