© 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. 10518
    Prev
    Next
    INDEX
    Explanations

    addresses and locations mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    symbols and punctuation used in dates and time-related contexts

    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
    ichick
    -0.80
     tack
    -0.73
     destro
    -0.70
     untouched
    -0.65
     deduct
    -0.64
     livest
    -0.64
     chest
    -0.63
     lying
    -0.62
    neck
    -0.62
     sack
    -0.62
    POSITIVE LOGITS
     OCT
    1.06
     JUL
    1.03
     Today
    1.02
     Following
    0.98
     Thousands
    0.96
     Yesterday
    0.93
    Today
    0.93
     APR
    0.93
    Following
    0.92
     Shortly
    0.92
    Activations Density 0.043%

    No Known Activations