© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16879
    Prev
    Next
    INDEX
    Explanations

    references to the term "ame"

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the word "name."

    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
     stabilization
    -0.69
     remote
    -0.65
     Reconstruction
    -0.64
     subjects
    -0.63
     taps
    -0.62
     farmers
    -0.62
     moving
    -0.60
     TTC
    -0.60
     conspir
    -0.60
     penetrating
    -0.60
    POSITIVE LOGITS
    ame
    4.61
    AME
    2.70
    ames
    2.55
    amed
    1.85
    aming
    1.73
    amer
    1.64
    ami
    1.35
    amous
    1.33
    amel
    1.32
    AMES
    1.31
    Activations Density 0.008%

    No Known Activations