© 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. 11-RES-JB
    11. 20406
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and business

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to classification or organization of events and entities

    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
    ravings
    -1.05
    osponsors
    -1.00
    tracks
    -0.93
    izons
    -0.88
    idelines
    -0.86
    votes
    -0.85
    aders
    -0.84
    models
    -0.83
    levels
    -0.82
    ometers
    -0.82
    POSITIVE LOGITS
     affair
    1.32
     endeavor
    1.09
     entity
    1.06
     phenomenon
    1.03
     undertaking
    0.97
     endeavour
    0.97
     proposition
    0.96
     piece
    0.96
     amalg
    0.95
     organism
    0.95
    Activations Density 0.292%

    No Known Activations