© 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. 11-RES-JB
    6. 2005
    Prev
    Next
    INDEX
    Explanations

    terms related to leadership and managerial roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to leadership roles and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sov
    -0.85
    nee
    -0.82
    enegger
    -0.77
     Neighbor
    -0.74
    ropolis
    -0.73
    thy
    -0.72
    agen
    -0.72
    iform
    -0.72
    onymous
    -0.71
    izer
    -0.71
    POSITIVE LOGITS
    ership
    0.96
     roles
    0.95
     positions
    0.94
     vacuum
    0.93
     qualities
    0.91
     aspirations
    0.91
     ambitions
    0.91
     vacancies
    0.88
     structure
    0.88
     position
    0.85
    Activations Density 0.104%

    No Known Activations