© 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. 11-RES-JB
    11. 4932
    Prev
    Next
    INDEX
    Explanations

    companies and organizations involved in oil exploration and production

    oai_token-act-pair · gpt-3.5-turbo

    references to state-owned enterprises and their acquisitions or operations in the global oil market

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ottesville
    -0.89
    pmwiki
    -0.86
    ipeg
    -0.80
    keyes
    -0.76
    atown
    -0.76
    Interstitial
    -0.75
    urrection
    -0.75
    alloween
    -0.74
    apixel
    -0.73
    utenberg
    -0.72
    POSITIVE LOGITS
     conglomerate
    1.34
     consortium
    1.22
     Petro
    1.17
     subsidiary
    1.09
     Gaz
    1.07
     subsidiaries
    1.07
     Mits
    1.06
     Ltd
    1.06
     Tata
    1.06
     Petroleum
    1.05
    Activations Density 0.421%

    No Known Activations