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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4761
    Prev
    Next
    INDEX
    Explanations

    names or keywords related to the name "Miley."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mil" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compr
    -0.84
    BOOK
    -0.78
    OPLE
    -0.77
    chnology
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    LY
    -0.69
    IELD
    -0.68
    eering
    -0.68
     Defenders
    -0.68
    ICLE
    -0.65
    POSITIVE LOGITS
    estones
    1.12
    estone
    1.05
    isec
    1.02
    ksh
    1.01
    waukee
    1.01
    gram
    0.96
    itaire
    0.90
    mud
    0.90
    itant
    0.90
    ilit
    0.89
    Activations Density 0.011%

    No Known Activations