© 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. 1-RES-JB
    11. 10269
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Nin" followed by a number, potentially related to a specific entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Ninety" or similar variants indicating the number ninety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HIP
    -0.75
     mileage
    -0.74
    Charges
    -0.67
     PRESS
    -0.66
    igating
    -0.65
     fault
    -0.65
     Redemption
    -0.64
    inventoryQuantity
    -0.63
    Single
    -0.62
     placement
    -0.62
    POSITIVE LOGITS
    eteen
    1.73
    eteenth
    1.63
    eties
    1.44
    jas
    1.37
    ety
    1.32
    ormal
    1.02
    omen
    1.00
    ishers
    0.99
    jah
    0.98
    ovember
    0.97
    Activations Density 0.005%

    No Known Activations