© 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. 19501
    Prev
    Next
    INDEX
    Explanations

    references to financial terminology, specifically related to ownership in companies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to equity in various contexts

    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
    slow
    -0.73
    ================================================================
    -0.68
    interface
    -0.68
    HCR
    -0.64
     Mild
    -0.63
    GMT
    -0.63
    OOK
    -0.62
    âĺ
    -0.62
    PIN
    -0.62
    cause
    -0.61
    POSITIVE LOGITS
    ilege
    0.95
     stakes
    0.86
     equity
    0.85
    inventoryQuantity
    0.81
     crowdfunding
    0.79
    itutional
    0.76
     compensation
    0.73
     privilege
    0.72
     ladder
    0.72
     stake
    0.72
    Activations Density 0.009%

    No Known Activations