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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1-RES-JB
    6. 9946
    Prev
    Next
    INDEX
    Explanations

    words related to financial schemes, specifically mentioning "Ponzi" and associated actions

    oai_token-act-pair · gpt-3.5-turbo

    references to Ponzi schemes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Borders
    -0.78
     Chief
    -0.66
     Sea
    -0.66
     Skull
    -0.65
    drawn
    -0.65
     Lauder
    -0.64
     Pixel
    -0.63
     Chr
    -0.62
     Midlands
    -0.62
     Primal
    -0.61
    POSITIVE LOGITS
    onz
    1.41
    alez
    1.15
    acci
    0.91
    aga
    0.90
    onis
    0.88
    osa
    0.84
    aily
    0.83
    avorite
    0.79
    kefeller
    0.79
    oshi
    0.79
    Activations Density 0.002%

    No Known Activations