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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 21557
    Prev
    Next
    INDEX
    Explanations

    mentions of subsidiaries and related business entities

    oai_token-act-pair · gpt-3.5-turbo

    references to corporate subsidiaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bra
    -0.79
    ttp
    -0.74
    hner
    -0.73
    ohan
    -0.70
    azon
    -0.69
    maxwell
    -0.65
     Hav
    -0.64
    acha
    -0.63
    bat
    -0.63
    match
    -0.62
    POSITIVE LOGITS
     subsidiary
    1.15
    rador
    1.01
     subsidiaries
    0.95
    unia
    0.88
     subcontract
    0.76
     headquartered
    0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.75
     owned
    0.74
     manag
    0.72
    BIL
    0.72
    Activations Density 0.012%

    No Known Activations