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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16745
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial and economic concepts, such as revenue, debt, spending, borrowing, deficits, and investments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "new" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Zip
    -0.77
    acebook
    -0.76
    istine
    -0.76
    xual
    -0.75
    ashtra
    -0.72
    aminer
    -0.72
    veyard
    -0.70
    ulhu
    -0.69
    OPA
    -0.68
    RPG
    -0.67
    POSITIVE LOGITS
    bies
    1.25
    bie
    1.13
     arrivals
    1.13
     entrants
    1.05
     additions
    1.00
     developments
    1.00
    foundland
    0.96
     Zealand
    0.94
     discoveries
    0.91
     hires
    0.88
    Activations Density 0.099%

    No Known Activations