© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2840
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of creating

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "creating" in various contexts

    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
    isance
    -0.71
    baugh
    -0.68
    ocular
    -0.66
    raph
    -0.62
    miss
    -0.62
    iolet
    -0.62
    hus
    -0.62
     fared
    -0.62
    orne
    -0.61
     Matters
    -0.61
    POSITIVE LOGITS
     creating
    3.08
    Creating
    2.21
     Creating
    2.11
     constructing
    1.95
     generating
    1.90
     designing
    1.89
     producing
    1.82
     forming
    1.72
     establishing
    1.70
     create
    1.70
    Activations Density 0.017%

    No Known Activations