© 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. 2652
    Prev
    Next
    INDEX
    Explanations

    references to lotteries

    oai_token-act-pair · gpt-3.5-turbo

    references to lottery systems and related processes

    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
     Aven
    -0.79
    pod
    -0.67
    unci
    -0.65
     Views
    -0.64
    ight
    -0.63
    contained
    -0.63
    urg
    -0.62
    ack
    -0.62
     Pod
    -0.62
    ears
    -0.60
    POSITIVE LOGITS
     lottery
    4.10
     Lot
    1.63
     gambling
    1.35
     gamble
    1.26
    Lot
    1.20
     casino
    1.10
     voucher
    1.10
     auction
    1.08
     poker
    1.06
     gamb
    1.04
    Activations Density 0.010%

    No Known Activations