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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13307
    Prev
    Next
    INDEX
    Explanations

    the name "Amy"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Amy" and variations of the word "famous" or "infamous."

    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
     Copper
    -0.68
     dra
    -0.68
     resource
    -0.66
     Glas
    -0.65
     respir
    -0.63
    Works
    -0.62
     Corps
    -0.62
     Dos
    -0.61
     Strip
    -0.61
     gas
    -0.60
    POSITIVE LOGITS
    amy
    5.02
    amous
    2.19
    AMY
    1.51
    omy
    1.32
     amy
    1.22
    aming
    1.20
    ami
    1.19
    amic
    1.17
    amia
    1.16
    AMS
    1.15
    Activations Density 0.011%

    No Known Activations