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. 9-RES-JB
    6. 21729
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial activities and transactions, particularly those involving investment or purchasing

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to financial transactions or investments

    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
     Confederation
    -0.74
     Chambers
    -0.74
     Fi
    -0.71
     Feder
    -0.69
     Continental
    -0.62
     Nicarag
    -0.61
     Kok
    -0.60
     provisional
    -0.60
     Imran
    -0.60
     Rounds
    -0.60
    POSITIVE LOGITS
    your
    1.32
    downs
    1.22
    outs
    1.15
    out
    1.13
    down
    1.13
    lease
    1.12
    offs
    1.09
    around
    1.08
    up
    1.05
    through
    1.04
    Activations Density 0.087%

    No Known Activations