© 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. 3-RES-JB
    11. 1915
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Oren" with varying degrees of intensity

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the substring "ren" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stakes
    -0.69
    !/
    -0.66
     Trinidad
    -0.65
     guts
    -0.60
     fateful
    -0.59
     gum
    -0.57
     Trash
    -0.57
     Hole
    -0.55
     Iranians
    -0.55
     eleph
    -0.54
    POSITIVE LOGITS
    fell
    0.99
    unci
    0.96
    nen
    0.95
    semble
    0.93
    esis
    0.92
    ault
    0.92
    cia
    0.90
    enberg
    0.86
    ren
    0.86
    unciation
    0.86
    Activations Density 0.009%

    No Known Activations