© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2608
    Prev
    Next
    INDEX
    Explanations

    numbers in the context of locations or names such as districts, areas, or events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numbers or entities, particularly those associated with the term "Six."

    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
    rawdownloadcloneembedreportprint
    -0.77
    webkit
    -0.74
     includ
    -0.74
    anwhile
    -0.73
    auder
    -0.71
     DOI
    -0.70
    OPLE
    -0.67
    BIP
    -0.66
    activity
    -0.65
    igation
    -0.65
    POSITIVE LOGITS
    teen
    1.27
     Hundred
    1.20
    een
    1.08
     Thousand
    1.04
     Mile
    0.97
     Seasons
    0.97
    teenth
    0.96
    fold
    0.96
     Eyes
    0.94
     Lives
    0.93
    Activations Density 0.058%

    No Known Activations