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. 8-RES-JB
    6. 4370
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific number of hours

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hours."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dinand
    -0.92
    LECT
    -0.77
    bard
    -0.73
    esan
    -0.69
    avoid
    -0.68
    geist
    -0.66
    ften
    -0.66
    founded
    -0.66
    lected
    -0.66
    Magikarp
    -0.65
    POSITIVE LOGITS
    glass
    1.26
     Ago
    0.86
    endment
    0.81
     logged
    0.75
     ILCS
    0.74
    urst
    0.73
     commute
    0.71
     elapsed
    0.68
    obic
    0.67
    Hours
    0.66
    Activations Density 0.041%

    No Known Activations