© 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. 6-RES-JB
    11. 17800
    Prev
    Next
    INDEX
    Explanations

    quotations or statements in a formal or academic style

    oai_token-act-pair · gpt-3.5-turbo

    instances of text formatting or structure, particularly punctuation or separators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lled
    -0.78
     derby
    -0.78
     drums
    -0.75
     Hai
    -0.66
     bot
    -0.66
     Savannah
    -0.65
     displeasure
    -0.64
     steroids
    -0.64
    orate
    -0.64
     elephant
    -0.62
    POSITIVE LOGITS
    "...
    1.00
    "âĢ¦
    0.99
    BRE
    0.87
    "[
    0.86
    Quote
    0.85
    Dist
    0.83
    Young
    0.82
    We
    0.82
    Technology
    0.81
    Today
    0.81
    Activations Density 0.213%

    No Known Activations