© 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. 726
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Cru" or variations of "Cru" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of vehicles and related brands, particularly those involving the word "Cru"

    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
     Helsinki
    -0.77
    enegger
    -0.74
     Afghans
    -0.69
    mable
    -0.69
     Stard
    -0.68
     Georgian
    -0.68
     Reggie
    -0.67
     Kush
    -0.66
     Persian
    -0.65
     Finnish
    -0.64
    POSITIVE LOGITS
    cible
    1.09
    Cru
    1.08
    isers
    1.00
     Cru
    0.98
    isin
    0.95
    cru
    0.94
    cial
    0.86
    hn
    0.86
    ven
    0.86
    voy
    0.85
    Activations Density 0.008%

    No Known Activations