© 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. 1-RES-JB
    11. 14226
    Prev
    Next
    INDEX
    Explanations

    the specific word "ami" at different activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities named "Tami" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moons
    -0.69
     Mississippi
    -0.67
     presidents
    -0.62
     Wildcats
    -0.62
     vaccines
    -0.61
    sie
    -0.61
     Half
    -0.60
     steroids
    -0.59
     Purs
    -0.59
     quizz
    -0.59
    POSITIVE LOGITS
    ami
    1.41
    ibo
    1.26
    emi
    1.06
    AMI
    1.03
    ihara
    0.96
    yah
    0.94
    isance
    0.94
    ña
    0.92
    uko
    0.91
    aria
    0.90
    Activations Density 0.005%

    No Known Activations