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. 1-RES-JB
    6. 19177
    Prev
    Next
    INDEX
    Explanations

    words related to a specific surname "Luster"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "buster"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cogn
    -0.65
    Copyright
    -0.65
     presumed
    -0.63
    edit
    -0.62
    Ĭ±
    -0.61
     assumes
    -0.60
     open
    -0.58
    credit
    -0.57
    spring
    -0.57
    book
    -0.57
    POSITIVE LOGITS
    uster
    0.96
    usters
    0.95
    avorite
    0.83
    fuck
    0.79
    culosis
    0.78
    rade
    0.76
    ansky
    0.76
    abwe
    0.75
    aber
    0.73
    aser
    0.72
    Activations Density 0.008%

    No Known Activations