© 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. 18040
    Prev
    Next
    INDEX
    Explanations

    the origin or place of origin of different concepts, rumors, and practices

    oai_token-act-pair · gpt-3.5-turbo

    the term "originated" and its variations in different contexts

    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
     tough
    -0.65
    fty
    -0.62
     Ashes
    -0.61
     close
    -0.60
     Add
    -0.58
     Hard
    -0.58
     feeling
    -0.57
    iling
    -0.57
     Beat
    -0.56
     grim
    -0.56
    POSITIVE LOGITS
     originated
    3.52
     originate
    2.80
     originating
    2.17
     origin
    1.63
     stemmed
    1.49
     arose
    1.44
     migrated
    1.37
     eman
    1.36
    origin
    1.35
     derives
    1.34
    Activations Density 0.008%

    No Known Activations