© 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. 3-RES-JB
    6. 9700
    Prev
    Next
    INDEX
    Explanations

    references to winning a lottery

    oai_token-act-pair · gpt-3.5-turbo

    references to lottery-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.74
    contained
    -0.72
    icz
    -0.70
    Civil
    -0.66
    20439
    -0.66
    english
    -0.65
     Idle
    -0.65
    eq
    -0.65
    strong
    -0.65
    sup
    -0.64
    POSITIVE LOGITS
     lottery
    1.05
    tery
    0.90
    eers
    0.89
     ticket
    0.76
     Lot
    0.76
     tickets
    0.74
    stakes
    0.72
     defenseman
    0.71
     Sharks
    0.70
     "$:/
    0.68
    Activations Density 0.006%

    No Known Activations