© 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. 7-RES-JB
    6. 18914
    Prev
    Next
    INDEX
    Explanations

    sports-related terms

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various sectors and institutions, particularly in health, sports, and law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.74
    terday
    -0.74
     flatt
    -0.74
    gered
    -0.69
    itably
    -0.69
    oxide
    -0.67
    arming
    -0.65
    ught
    -0.64
    ocobo
    -0.64
     convincing
    -0.64
    POSITIVE LOGITS
     Department
    1.10
     Services
    1.04
     Clause
    1.01
     Room
    1.00
     Bureau
    0.98
     Accountability
    0.97
     Sciences
    0.95
     Matters
    0.95
     Club
    0.94
     Service
    0.94
    Activations Density 0.259%

    No Known Activations