Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 20549
    Prev
    Next
    INDEX
    Explanations

    the word 'Lot' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Lot" or variations of it, indicating a focus on lottery references

    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
     reach
    -0.66
    ielding
    -0.66
     resolve
    -0.64
     exert
    -0.63
     cables
    -0.62
    __
    -0.62
    heastern
    -0.60
     accompan
    -0.58
    chen
    -0.58
     serve
    -0.58
    POSITIVE LOGITS
     Lot
    4.30
    Lot
    2.58
     LOT
    1.83
    lot
    1.79
     lottery
    1.66
     Lots
    1.36
     Slot
    1.17
     lot
    1.06
     Auction
    0.98
     Toll
    0.95
    Activations Density 0.023%

    No Known Activations