© 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. 11789
    Prev
    Next
    INDEX
    Explanations

    words related to artificial intelligence

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence

    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
     windows
    -0.70
     quint
    -0.69
     sandwich
    -0.68
     sexually
    -0.65
     weekend
    -0.65
     cond
    -0.63
     fin
    -0.62
     tub
    -0.61
     bread
    -0.61
     tarn
    -0.61
    POSITIVE LOGITS
    AI
    4.42
     AI
    1.96
    AE
    1.50
    AIR
    1.28
    IU
    1.27
    IQ
    1.22
    UI
    1.21
    AAF
    1.21
    AU
    1.18
     Artificial
    1.18
    Activations Density 0.013%

    No Known Activations