© 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. 4-RES-JB
    11. 9420
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and law enforcement matters, such as legislation, awards, and security issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of tests, assessments, and categorizations

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

    No Comments

    Negative Logits
     showc
    -0.88
     carbohyd
    -0.85
     tremend
    -0.82
     toget
    -0.77
     gobl
    -0.77
    etheless
    -0.76
     idle
    -0.75
     respons
    -0.73
     disg
    -0.71
    amous
    -0.70
    POSITIVE LOGITS
     Association
    1.16
     Coordinator
    1.04
     Club
    1.00
     Index
    0.99
     Simulator
    0.99
     Foundation
    0.99
     Suite
    0.96
     Tracker
    0.95
     Service
    0.94
     Authority
    0.94
    Activations Density 0.298%

    No Known Activations