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. 7784
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly relating to business or finance

    oai_token-act-pair · gpt-3.5-turbo

    references to Warren Buffett and his association with Berkshire Hathaway

    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
    pter
    -0.80
    ĪĴ
    -0.77
    ories
    -0.76
    fully
    -0.70
    FTWARE
    -0.69
    ORY
    -0.68
    RT
    -0.67
    phis
    -0.66
     skelet
    -0.65
     psychiat
    -0.65
    POSITIVE LOGITS
     Buffett
    1.16
    etts
    0.89
     Berkshire
    0.81
     Hath
    0.80
    leneck
    0.77
    olini
    0.76
     Buff
    0.76
    ulously
    0.75
    oken
    0.75
     dividends
    0.74
    Activations Density 0.011%

    No Known Activations