© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 13973
    Prev
    Next
    INDEX
    Explanations

    the number "two" occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities, specifically the numbers "two", "three", and "four"

    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
     Caption
    -0.87
    displayText
    -0.71
    aukee
    -0.70
    helps
    -0.68
    IAS
    -0.66
    rolet
    -0.65
    lov
    -0.64
    gerald
    -0.63
    asta
    -0.61
    LES
    -0.61
    POSITIVE LOGITS
     dimensional
    1.24
    dimensional
    1.10
    fold
    1.08
     sided
    1.06
     thirds
    1.04
    teenth
    1.01
     continents
    1.00
     thumbs
    0.95
     fingers
    0.94
     legs
    0.93
    Activations Density 0.156%

    No Known Activations