© 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. 10-RES-JB
    11. 5116
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word 'one' indicating singularity or priority

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing unity or the concept of being one

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lov
    -0.75
    ears
    -0.73
    ãĤ¬
    -0.73
    ãĥ©ãĥ³
    -0.68
    2003
    -0.63
    def
    -0.62
    ãĥ¼ãĥ
    -0.61
    ories
    -0.60
    ãĤº
    -0.59
    papers
    -0.59
    POSITIVE LOGITS
     sided
    1.07
     dimensional
    0.98
    dimensional
    0.91
     thing
    0.91
     hundred
    0.86
     Hundred
    0.84
     cohesive
    0.79
     step
    0.76
     heck
    0.75
     thousand
    0.73
    Activations Density 0.079%

    No Known Activations