© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 13885
    Prev
    Next
    INDEX
    Explanations

    mentions of seasonal activities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to seasonal occurrences or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chun
    -0.71
     Elect
    -0.70
    ront
    -0.69
     Quan
    -0.68
    ording
    -0.68
    MK
    -0.65
     Command
    -0.60
    Tech
    -0.60
    ieved
    -0.59
     OK
    -0.59
    POSITIVE LOGITS
     seasonal
    3.62
    Season
    1.30
    season
    1.30
     festive
    1.22
     winter
    1.20
     Season
    1.18
    holiday
    1.15
    Winter
    1.14
     Seasons
    1.13
     holiday
    1.12
    Activations Density 0.018%

    No Known Activations