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. 2-RES-JB
    6. 2660
    Prev
    Next
    INDEX
    Explanations

    proper names, likely related to politics, businesses, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rus" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.72
    opsy
    -0.69
    ĺħ
    -0.68
     vested
    -0.65
    ¿½
    -0.63
    holder
    -0.62
     conspicuous
    -0.61
     respected
    -0.61
     removable
    -0.61
     accessory
    -0.60
    POSITIVE LOGITS
    kies
    1.13
     Rus
    1.07
    byss
    1.02
    sel
    0.96
    coe
    0.90
    ques
    0.90
    kin
    0.86
    kie
    0.86
    Rus
    0.84
    iets
    0.83
    Activations Density 0.006%

    No Known Activations