© 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. 17465
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to "Re" as a prefix or abbreviation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Re"

    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
     GEAR
    -0.74
     Anchorage
    -0.70
    ONES
    -0.64
     handwriting
    -0.62
     AAA
    -0.61
    ãģĨ
    -0.61
     NEC
    -0.61
     Ukrain
    -0.60
    ãĤĬ
    -0.59
     Corpus
    -0.59
    POSITIVE LOGITS
    becca
    1.49
    asons
    1.46
    levant
    1.38
    ceived
    1.31
    verend
    1.28
    asonable
    1.28
    ggie
    1.26
    venge
    1.26
    ceiver
    1.23
    venue
    1.21
    Activations Density 0.012%

    No Known Activations