© 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. 0-RES-JB
    11. 13935
    Prev
    Next
    INDEX
    Explanations

    terms related to artificial intelligence (AI)

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence and its related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renew
    -0.80
     renewal
    -0.77
     Tub
    -0.68
     satisf
    -0.67
    rero
    -0.66
    adelphia
    -0.65
    stru
    -0.64
    yrs
    -0.64
    fif
    -0.64
    gall
    -0.63
    POSITIVE LOGITS
     AI
    3.72
    AI
    2.46
     Artificial
    1.80
     bots
    1.48
     NPC
    1.38
     automation
    1.37
     NPCs
    1.31
     Siri
    1.28
     artificial
    1.28
     robots
    1.21
    Activations Density 0.009%

    No Known Activations