© 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. 7179
    Prev
    Next
    INDEX
    Explanations

    words related to inventing or creating new things

    oai_token-act-pair · gpt-3.5-turbo

    instances related to invention and creativity

    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
    Installation
    -0.66
    cffffcc
    -0.62
     Warden
    -0.62
     Dah
    -0.61
    swer
    -0.59
     Nieto
    -0.59
     Ibid
    -0.58
    expected
    -0.58
     Returning
    -0.58
    hunter
    -0.58
    POSITIVE LOGITS
    ories
    1.30
    arus
    1.15
    iveness
    1.14
    ively
    1.01
    ivity
    0.98
     invent
    0.94
    iating
    0.94
    iencies
    0.91
    iates
    0.90
    ors
    0.89
    Activations Density 0.010%

    No Known Activations