© 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. 3-RES-JB
    11. 11204
    Prev
    Next
    INDEX
    Explanations

    phrases related to data centers

    oai_token-act-pair · gpt-3.5-turbo

    references to "data" or "datacenter"

    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
    âķIJ
    -0.84
     tremend
    -0.67
     erect
    -0.66
     piercing
    -0.64
    ducers
    -0.64
     Mutual
    -0.62
    zzi
    -0.61
     Palmer
    -0.61
    ModLoader
    -0.61
    IDES
    -0.61
    POSITIVE LOGITS
    abases
    1.36
    etime
    1.03
    Dat
    1.00
    eman
    0.95
    dat
    0.94
    alog
    0.87
    herer
    0.87
    iverse
    0.87
     Dat
    0.86
    amation
    0.82
    Activations Density 0.010%

    No Known Activations