© 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. 4-RES-JB
    6. 14345
    Prev
    Next
    INDEX
    Explanations

    financial transactions involving buying and selling of assets or securities

    oai_token-act-pair · gpt-3.5-turbo

    references to buying activities and financial transactions

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

    No Comments

    Negative Logits
    uality
    -0.88
    icone
    -0.75
    immer
    -0.74
    ensis
    -0.72
     Symptoms
    -0.72
    ogen
    -0.71
    Sym
    -0.69
    icho
    -0.69
    osa
    -0.67
    doi
    -0.67
    POSITIVE LOGITS
     buying
    0.83
     spree
    0.79
     financing
    0.78
     buy
    0.77
     footing
    0.77
     investors
    0.75
     financed
    0.75
     advisers
    0.75
    iture
    0.74
     buys
    0.73
    Activations Density 0.042%

    No Known Activations