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. 10-RES-JB
    6. 18098
    Prev
    Next
    INDEX
    Explanations

    time-related references, such as years and periods of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating approximate timeframes or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ole
    -0.69
    oly
    -0.68
    ociation
    -0.67
    jay
    -0.66
    ious
    -0.65
     Difference
    -0.64
    ulum
    -0.63
    ococ
    -0.63
    ffen
    -0.63
    Cs
    -0.62
    POSITIVE LOGITS
     halfway
    1.16
     fortnight
    1.04
     weeks
    0.98
     decade
    0.96
     noon
    0.93
     ten
    0.93
     six
    0.92
     months
    0.92
     seven
    0.92
     fifteen
    0.91
    Activations Density 0.077%

    No Known Activations