© 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. 13028
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Ponzi scheme"

    oai_token-act-pair · gpt-3.5-turbo

    references to fraudulent schemes, particularly Ponzi schemes

    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
     Borders
    -0.75
     Lauder
    -0.71
     Primal
    -0.65
     Chief
    -0.62
     Outside
    -0.61
     SPORTS
    -0.61
     Wond
    -0.60
    Wall
    -0.60
     WOM
    -0.60
    houses
    -0.59
    POSITIVE LOGITS
    onz
    1.26
    alez
    1.21
    onis
    0.87
    osa
    0.85
    aily
    0.82
    oshi
    0.81
    aga
    0.80
    acca
    0.78
    ework
    0.78
    acci
    0.78
    Activations Density 0.005%

    No Known Activations