© 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. 3-RES-JB
    6. 12809
    Prev
    Next
    INDEX
    Explanations

    words related to leadership roles or titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles within organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roman
    -0.82
     queen
    -0.72
    iannopoulos
    -0.67
    aping
    -0.67
    aunder
    -0.66
     avalanche
    -0.65
     maiden
    -0.65
     tremend
    -0.65
    days
    -0.64
     sensit
    -0.64
    POSITIVE LOGITS
     Manager
    1.15
     Candidate
    1.07
     Coordinator
    1.06
     Leader
    1.01
     Officer
    0.99
     Assistant
    0.97
     Agent
    0.97
     Mode
    0.95
     Director
    0.95
     Branch
    0.94
    Activations Density 0.071%

    No Known Activations