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. 2-RES-JB
    6. 8471
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Juliet"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific suffix or pattern in words, particularly "iet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shattered
    -0.77
    Hour
    -0.77
    manship
    -0.77
    SPONSORED
    -0.74
    CONCLUS
    -0.68
    older
    -0.65
     situ
    -0.65
     fracturing
    -0.63
     tampering
    -0.62
     Chosen
    -0.62
    POSITIVE LOGITS
    oleon
    1.33
    namese
    1.23
    zsche
    1.20
    iet
    1.19
    rition
    0.98
    ocol
    0.96
    rix
    0.88
    alia
    0.88
    chen
    0.87
    rina
    0.86
    Activations Density 0.006%

    No Known Activations