© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 18635
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial exchanges

    oai_token-act-pair · gpt-3.5-turbo

    mentions of exchanges related to financial transactions, particularly in cryptocurrency

    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
    IGHTS
    -0.83
    jac
    -0.74
    Äĩ
    -0.73
    idis
    -0.73
    ILL
    -0.70
    ardi
    -0.70
    DIR
    -0.69
    oeuv
    -0.67
    sbm
    -0.67
    à©
    -0.67
    POSITIVE LOGITS
     exchange
    0.96
     traded
    0.89
    places
    0.89
    daq
    0.88
    prise
    0.83
     ledger
    0.83
     Royale
    0.80
     regulator
    0.80
     exchanges
    0.77
    rencies
    0.76
    Activations Density 0.016%

    No Known Activations