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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 22914
    Prev
    Next
    INDEX
    Explanations

    references to the concept of money or currency

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary transactions or cash-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lov
    -0.75
     Oz
    -0.73
    £ı
    -0.71
     Fav
    -0.70
     Emin
    -0.70
     Galile
    -0.68
     Reborn
    -0.67
     Sabb
    -0.66
     Ples
    -0.65
     Stru
    -0.65
    POSITIVE LOGITS
    mere
    1.26
     infusion
    0.94
    flow
    0.91
     flow
    0.87
    holder
    0.84
     flows
    0.82
     receipts
    0.82
     withdrawals
    0.82
    iers
    0.81
     strapped
    0.80
    Activations Density 0.032%

    No Known Activations