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. 6-RES-JB
    6. 11286
    Prev
    Next
    INDEX
    Explanations

    the end of a time period or event in text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "end" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.69
    dinand
    -0.69
    kaya
    -0.68
    ufact
    -0.68
     Inqu
    -0.67
    æ©Ł
    -0.65
    uni
    -0.64
    avorite
    -0.63
    chy
    -0.62
    pread
    -0.61
    POSITIVE LOGITS
    owment
    1.14
    ocrine
    1.02
    ocrin
    0.90
    game
    0.88
    notes
    0.87
    angered
    0.85
    angering
    0.84
    orses
    0.83
    points
    0.83
     thereof
    0.81
    Activations Density 0.027%

    No Known Activations