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. 18213
    Prev
    Next
    INDEX
    Explanations

    mentions of specific holidays, such as Thanksgiving and Valentine's Day

    oai_token-act-pair · gpt-3.5-turbo

    references to Thanksgiving and related holidays

    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
    ially
    -0.88
     constitu
    -0.87
    ioch
    -0.84
    ials
    -0.76
    upon
    -0.74
    etting
    -0.71
    umbn
    -0.69
     defin
    -0.69
    erd
    -0.69
    iological
    -0.68
    POSITIVE LOGITS
     eve
    0.97
     Day
    0.95
     Eve
    0.92
     festivities
    0.86
     Thanksgiving
    0.84
     Month
    0.83
    nesday
    0.83
     holidays
    0.82
     dinner
    0.82
     Surprise
    0.81
    Activations Density 0.012%

    No Known Activations