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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 684
    Prev
    Next
    INDEX
    Explanations

    names related to technology industry leaders

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and companies

    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
     Confederate
    -0.85
     constitu
    -0.80
     totality
    -0.78
     deport
    -0.77
     poems
    -0.77
     canon
    -0.76
     poem
    -0.76
     poss
    -0.76
     rhy
    -0.75
     republican
    -0.74
    POSITIVE LOGITS
    Shares
    1.39
     Labs
    1.16
     startups
    1.10
    Bitcoin
    1.09
    Business
    1.06
     Developers
    1.05
    Companies
    1.00
    Market
    1.00
    Coin
    1.00
     Investment
    0.99
    Activations Density 0.422%

    No Known Activations