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. 21220
    Prev
    Next
    INDEX
    Explanations

    specific time zone offsets such as UTC values

    oai_token-act-pair · gpt-3.5-turbo

    references to time zones and scheduling

    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
    Interstitial
    -0.81
    idas
    -0.75
    taboola
    -0.74
    soDeliveryDate
    -0.68
    ores
    -0.66
    hus
    -0.66
    cig
    -0.66
    adeon
    -0.65
    ogram
    -0.64
    enegger
    -0.62
    POSITIVE LOGITS
    UTC
    1.26
     UTC
    0.73
     shif
    0.72
    âĨij
    0.66
    hement
    0.66
    RFC
    0.64
     archived
    0.62
     Gamergate
    0.62
     discretion
    0.62
    farious
    0.61
    Activations Density 0.017%

    No Known Activations