© 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. 9-RES-JB
    11. 9001
    Prev
    Next
    INDEX
    Explanations

    keywords related to finance and income, particularly revenue-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial income and revenue generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.97
    tons
    -0.71
    uran
    -0.69
    rane
    -0.69
    creen
    -0.68
    ãĤ¨ãĥ«
    -0.67
    POS
    -0.67
    Ò
    -0.64
    igo
    -0.63
     Barber
    -0.63
    POSITIVE LOGITS
     streams
    1.20
     stream
    0.96
     revenues
    0.95
     revenue
    0.91
     shortfall
    0.86
     generated
    0.85
     projections
    0.84
    flow
    0.83
     receipts
    0.82
     expenditure
    0.81
    Activations Density 0.029%

    No Known Activations