© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 350
    Prev
    Next
    INDEX
    Explanations

    information about ownership or affiliation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ownership and possession of companies or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urai
    -0.91
    enegger
    -0.86
    ople
    -0.85
    urnal
    -0.81
    obo
    -0.76
    icho
    -0.74
    obic
    -0.72
     guiActiveUn
    -0.70
    osen
    -0.69
    gomery
    -0.69
    POSITIVE LOGITS
     subsidiary
    0.98
     subsidiaries
    0.96
    holding
    0.86
    ership
    0.85
     slaves
    0.84
     property
    0.84
    Property
    0.83
     owned
    0.83
     stake
    0.80
     stakes
    0.78
    Activations Density 0.050%

    No Known Activations