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

    Neuronpedia

    Jacobian LensNEW
    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. 1833
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of creation or beginning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of creation

    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
    oulos
    -0.81
    andowski
    -0.80
     Rosenberg
    -0.75
     Abram
    -0.74
    Uber
    -0.74
    azard
    -0.72
    atra
    -0.71
     Rubin
    -0.71
    stein
    -0.71
    aez
    -0.71
    POSITIVE LOGITS
     cre
    3.82
     Cre
    1.53
    cre
    1.50
     cream
    1.35
    Cre
    1.33
     sque
    1.20
     creed
    1.04
     crest
    1.02
     stre
    1.01
     cracks
    1.01
    Activations Density 0.016%

    No Known Activations