© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15223
    Prev
    Next
    INDEX
    Explanations

    phrases related to companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Inc." or various forms of "Inc." in company names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.72
    */(
    -0.70
    assetsadobe
    -0.70
     Marketable
    -0.69
    hack
    -0.69
    yards
    -0.69
    hu
    -0.68
    hari
    -0.68
    \\\\\\\\
    -0.67
     Unch
    -0.67
    POSITIVE LOGITS
    orporated
    1.44
    redibly
    1.23
    identally
    1.22
    orpor
    1.18
    arcer
    1.15
    ursions
    1.10
    ursion
    1.08
    redible
    1.04
    inct
    1.03
    idental
    1.02
    Activations Density 0.008%

    No Known Activations