© 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. 9-RES-JB
    11. 14109
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "cre" along with its variations

    oai_token-act-pair · gpt-3.5-turbo

    the word "cre" in various contexts, which appears to be part of a larger set of phrases or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.79
     GOODMAN
    -0.72
    manship
    -0.68
    STER
    -0.67
     buckle
    -0.63
     mileage
    -0.63
     buck
    -0.62
     Respond
    -0.60
     THR
    -0.59
     Titanic
    -0.58
    POSITIVE LOGITS
    ighton
    1.29
    eping
    1.12
    aky
    1.09
    vice
    1.06
    ased
    1.02
    aking
    0.99
    ase
    0.96
    ndra
    0.94
    pes
    0.93
    ations
    0.93
    Activations Density 0.038%

    No Known Activations