© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10453
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Miranda"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Miranda."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sg
    -0.89
    ded
    -0.79
    swing
    -0.76
    ERAL
    -0.75
    lopp
    -0.74
    tc
    -0.74
    ensible
    -0.74
    proc
    -0.72
    CAST
    -0.72
    eled
    -0.71
    POSITIVE LOGITS
     Miranda
    1.16
     Guer
    0.77
    iola
    0.76
     Leilan
    0.76
     Sturgeon
    0.75
    ignt
    0.74
    igans
    0.74
     Lambert
    0.71
     Martinez
    0.71
    ÃŃn
    0.70
    Activations Density 0.004%

    No Known Activations