© 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. 7-RES-JB
    11. 3585
    Prev
    Next
    INDEX
    Explanations

    keywords related to private sectors and equity firms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the private sector and its interactions with various industries, particularly in finance and healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¯ãĥ³
    -0.76
    ر
    -0.69
    Writer
    -0.68
    aston
    -0.66
    alos
    -0.66
    witz
    -0.66
     Conver
    -0.66
    onday
    -0.66
     Yamato
    -0.65
     Ragnarok
    -0.65
    POSITIVE LOGITS
     qui
    0.66
     contractors
    0.64
     corporations
    0.63
     oath
    0.63
     behold
    0.62
     bond
    0.60
    Īè
    0.60
     servants
    0.60
    âĢ¢âĢ¢
    0.60
     exercising
    0.60
    Activations Density 0.164%

    No Known Activations