© 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. 2-RES-JB
    6. 13678
    Prev
    Next
    INDEX
    Explanations

    phrases related to companies and business operations

    oai_token-act-pair · gpt-3.5-turbo

    references to companies in various contexts

    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
    rawdownloadcloneembedreportprint
    -0.71
    theless
    -0.68
     Maw
    -0.66
    718
    -0.66
     RELEASE
    -0.66
    lihood
    -0.65
    bound
    -0.65
     Fulton
    -0.65
     [|
    -0.64
     LIB
    -0.64
    POSITIVE LOGITS
     executives
    1.06
     companies
    0.98
    afety
    0.93
     firms
    0.91
     nomine
    0.89
     mogul
    0.88
     CEOs
    0.87
     corporations
    0.85
     enterprises
    0.82
    mens
    0.79
    Activations Density 0.026%

    No Known Activations