Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 255
    Prev
    Next
    INDEX
    Explanations

    terms related to financial matters, particularly the treasury and coffers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial entities and accounts

    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
     Observ
    -0.76
     Sutton
    -0.75
     Amateur
    -0.75
     Subst
    -0.74
     Television
    -0.74
     Pitch
    -0.72
     Differences
    -0.71
     Detection
    -0.70
     Ole
    -0.67
     Nig
    -0.66
    POSITIVE LOGITS
     coffers
    2.55
     treasury
    2.51
     treasurer
    2.14
     Treasurer
    1.50
     bankrupt
    1.20
    arium
    1.04
     senate
    1.00
     vault
    0.94
    ultimate
    0.94
     furnace
    0.94
    Activations Density 0.056%

    No Known Activations