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. 17226
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or activities related to amateurism

    oai_token-act-pair · gpt-3.5-turbo

    references to amateurism and beginner-level participation

    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
     Archdemon
    -0.71
    uncture
    -0.64
     Doors
    -0.64
    ha
    -0.64
    dated
    -0.63
    ãĥķãĤ©
    -0.62
    appy
    -0.62
    metics
    -0.62
    oran
    -0.62
    ean
    -0.61
    POSITIVE LOGITS
     amateur
    1.15
    ateurs
    1.14
     Amateur
    1.07
    ateur
    0.97
    IFIED
    0.91
     hobby
    0.79
    sterdam
    0.77
    blers
    0.77
    WithNo
    0.76
    ishly
    0.73
    Activations Density 0.007%

    No Known Activations