© 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. 2-RES-JB
    11. 23790
    Prev
    Next
    INDEX
    Explanations

    titles or roles related to product management in corporate settings

    oai_token-act-pair · gpt-3.5-turbo

    references to various managerial positions

    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
    iannopoulos
    -0.94
    >>>>>>>>
    -0.78
    otine
    -0.76
     republican
    -0.73
    =-=-=-=-=-=-=-=-
    -0.73
    utsche
    -0.71
    itious
    -0.70
    psey
    -0.66
    ĸļ
    -0.66
    itional
    -0.66
    POSITIVE LOGITS
     Manager
    1.08
     Management
    0.91
     Operator
    0.89
     Administrator
    0.87
     Accounts
    0.84
     Configuration
    0.84
     Simulator
    0.84
     Procedure
    0.84
     Administration
    0.83
     Operations
    0.83
    Activations Density 0.018%

    No Known Activations