Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 747
    Prev
    Next
    INDEX
    Explanations

    words related to policies, positions, and roles in organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and organizational roles, particularly in policy and management contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estamp
    -0.68
     whiff
    -0.68
     mug
    -0.68
    pload
    -0.66
     itch
    -0.63
     attm
    -0.63
    Rated
    -0.62
     clip
    -0.60
    Ü
    -0.60
    Pg
    -0.59
    POSITIVE LOGITS
     affairs
    1.02
     Operations
    0.97
     Affairs
    0.94
     Programs
    0.92
     communications
    0.83
     operations
    0.83
     Relations
    0.83
     consulting
    0.81
    relations
    0.81
     Marketing
    0.78
    Activations Density 0.159%

    No Known Activations