© 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. 2-RES-JB
    11. 17710
    Prev
    Next
    INDEX
    Explanations

    words related to splitting, dividing, or separating something into two or more parts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "split" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jamin
    -0.81
    Adv
    -0.71
    externalActionCode
    -0.70
    Grade
    -0.66
    vez
    -0.66
    psc
    -0.66
     Ven
    -0.62
    FORE
    -0.62
    Quantity
    -0.62
    trak
    -0.62
    POSITIVE LOGITS
    Split
    0.98
     split
    0.96
    ters
    0.91
     SPL
    0.90
     splits
    0.90
    split
    0.89
     hairs
    0.83
    tered
    0.75
     peas
    0.75
     splitting
    0.75
    Activations Density 0.011%

    No Known Activations