© 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. 17294
    Prev
    Next
    INDEX
    Explanations

    mathematical and computational terminology and expressions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to statistical functions and distributions

    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
     whistlebl
    -0.94
    bsite
    -0.77
    Website
    -0.76
    outube
    -0.73
    laun
    -0.73
     forums
    -0.71
    forum
    -0.71
     Sang
    -0.70
     cringe
    -0.70
    forums
    -0.69
    POSITIVE LOGITS
     theorem
    1.47
     algebra
    1.39
     arithmetic
    1.36
     integers
    1.35
     \(
    1.29
     coefficients
    1.28
     \(\
    1.28
     $\
    1.27
     exponent
    1.25
     multiplication
    1.21
    Activations Density 0.482%

    No Known Activations