© 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. 10-RES-JB
    11. 11288
    Prev
    Next
    INDEX
    Explanations

    numerical time and programming language-like tokens

    oai_token-act-pair · gpt-3.5-turbo

    time and date information related to sporting events

    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
    inventoryQuantity
    -0.72
    Secure
    -0.62
    Bloom
    -0.61
    Entry
    -0.57
    NetMessage
    -0.57
    limits
    -0.57
    Standard
    -0.56
    tim
    -0.55
    porary
    -0.55
    oops
    -0.54
    POSITIVE LOGITS
     13
    1.09
     5
    1.09
     8
    1.09
     6
    1.09
     11
    1.07
     17
    1.07
     39
    1.05
     9
    1.05
     14
    1.04
     23
    1.04
    Activations Density 0.072%

    No Known Activations