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. 4-RES-JB
    6. 22942
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of funds and finance

    oai_token-act-pair · gpt-3.5-turbo

    references to various funds and funding initiatives

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

    No Comments

    Negative Logits
    èª
    -0.77
    WithNo
    -0.72
    Magikarp
    -0.67
     Nieto
    -0.67
    âĹ¼
    -0.65
    theless
    -0.64
     apparel
    -0.64
     Halls
    -0.63
    çīĪ
    -0.62
    Else
    -0.62
    POSITIVE LOGITS
    ament
    1.50
    amental
    1.36
    raising
    1.31
    aments
    1.15
    fund
    1.08
    ributes
    0.87
    rolled
    0.86
    acion
    0.85
    rition
    0.85
    enges
    0.84
    Activations Density 0.016%

    No Known Activations