© 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. 0-RES-JB
    6. 15486
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Piretti"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific name or concept, likely related to a person or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dat
    -0.76
     Sek
    -0.75
    hou
    -0.73
     FANTASY
    -0.72
    zynski
    -0.71
    uch
    -0.70
     Malk
    -0.70
     Scal
    -0.69
    Las
    -0.69
    ASON
    -0.68
    POSITIVE LOGITS
     attitudes
    1.41
     compass
    1.37
     Compass
    1.27
    tti
    1.25
     Dart
    1.17
     ferry
    1.08
     raft
    1.00
     Ada
    0.95
     Polly
    0.94
    ioned
    0.92
    Activations Density 0.058%

    No Known Activations