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. 9-RES-JB
    6. 15157
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of time, specifically focused on the future

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "future."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.72
    paio
    -0.71
    yrics
    -0.62
    lua
    -0.62
    rency
    -0.61
    emis
    -0.60
    utters
    -0.60
    ldon
    -0.60
     Converted
    -0.59
    inic
    -0.59
    POSITIVE LOGITS
     tense
    0.89
     editions
    0.74
     installments
    0.73
     generations
    0.72
     iterations
    0.66
    .''.
    0.66
     onwards
    0.66
     phases
    0.65
    ebin
    0.65
    oscope
    0.63
    Activations Density 0.059%

    No Known Activations