© 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. 2-RES-JB
    11. 21636
    Prev
    Next
    INDEX
    Explanations

    phrases related to vehicles or products with 'Cru' as a part of the name

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Cruiser" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Helsinki
    -0.78
     Afghans
    -0.78
     Afghan
    -0.74
     Georgian
    -0.74
    enegger
    -0.71
     Kush
    -0.69
     Reggie
    -0.67
     Isis
    -0.65
     Taliban
    -0.65
     Finnish
    -0.65
    POSITIVE LOGITS
    Cru
    1.21
    cru
    1.12
     Cru
    1.10
    cible
    1.09
    isers
    1.06
    ciating
    0.99
    vic
    0.94
    ises
    0.94
     cru
    0.94
    isin
    0.93
    Activations Density 0.009%

    No Known Activations