© 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. 9-RES-JB
    11. 10085
    Prev
    Next
    INDEX
    Explanations

    names or references related to the name "Amie"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the word "am"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affairs
    -0.66
     kinderg
    -0.64
     melts
    -0.62
    yi
    -0.61
     sober
    -0.60
     resemb
    -0.60
     stakes
    -0.59
     strawberries
    -0.59
     puberty
    -0.59
     checkout
    -0.58
    POSITIVE LOGITS
    endment
    1.28
    nesty
    1.21
    bitious
    1.15
    sterdam
    1.14
    ilies
    1.14
    azing
    1.11
    pling
    1.10
    essage
    1.06
    otor
    1.06
    urai
    1.05
    Activations Density 0.065%

    No Known Activations