© 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. 17078
    Prev
    Next
    INDEX
    Explanations

    references to the word "Million"

    oai_token-act-pair · gpt-3.5-turbo

    the specific term "Mill 2."

    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
     manifest
    -0.68
     reass
    -0.67
     compr
    -0.67
     compelling
    -0.64
     Bind
    -0.64
    ---------------
    -0.64
    >>>>>>>>
    -0.63
     effected
    -0.61
     bondage
    -0.58
     rendition
    -0.57
    POSITIVE LOGITS
    enium
    1.84
    imet
    1.41
    imeter
    1.39
    isec
    1.29
    imeters
    1.29
    ennial
    1.28
    icent
    1.25
    inery
    1.23
    iard
    1.20
    enn
    1.17
    Activations Density 0.033%

    No Known Activations