© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6817
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial instruments, specifically bond investments

    oai_token-act-pair · gpt-3.5-turbo

    references to financial instruments, specifically bonds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    around
    -1.13
    mal
    -0.74
     airstrike
    -0.73
     ï
    -0.72
    ista
    -0.70
    gallery
    -0.67
     clinic
    -0.67
    call
    -0.67
    translation
    -0.67
    cial
    -0.66
    POSITIVE LOGITS
     bonds
    2.66
     Bonds
    1.72
    Tags
    1.71
    tags
    1.58
     Tags
    1.52
     tags
    1.49
     restraints
    1.14
     Garrett
    1.08
    chains
    1.06
     chains
    1.04
    Activations Density 0.019%

    No Known Activations