© 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. 988
    Prev
    Next
    INDEX
    Explanations

    references to the website "amazon.com" and the keyword "inland"

    oai_token-act-pair · gpt-4-turbo

    web links containing the word "amazon"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Amazon brand or service

    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
    ©¶æ
    -0.82
    oshenko
    -0.78
    ĵĺ
    -0.76
    âĶĢâĶĢâĶĢâĶĢ
    -0.75
    seless
    -0.75
     guiActiveUn
    -0.74
    veyard
    -0.71
    acco
    -0.71
     Toast
    -0.68
    Ń·
    -0.66
    POSITIVE LOGITS
    amazon
    1.07
    assetsadobe
    0.87
    clinton
    0.82
    ciation
    0.79
    dylib
    0.78
    worthiness
    0.76
    artments
    0.75
    cial
    0.71
    iband
    0.67
    tnc
    0.66
    Activations Density 0.019%

    No Known Activations