© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 23947
    Prev
    Next
    INDEX
    Explanations

    mentions of winning or playing the lottery

    oai_token-act-pair · gpt-3.5-turbo

    references to the lottery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contained
    -0.73
    icz
    -0.73
    stood
    -0.71
    english
    -0.69
    20439
    -0.68
    cam
    -0.68
    eq
    -0.68
    owicz
    -0.67
    icas
    -0.66
    sis
    -0.66
    POSITIVE LOGITS
     lottery
    1.17
    tery
    0.94
    eers
    0.89
     Lot
    0.83
     ticket
    0.81
    stakes
    0.79
     tickets
    0.73
     Sabha
    0.71
     pool
    0.67
     Sharks
    0.67
    Activations Density 0.006%

    No Known Activations