© 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. 1-RES-JB
    11. 3393
    Prev
    Next
    INDEX
    Explanations

    verbs related to division or separation

    oai_token-act-pair · gpt-3.5-turbo

    instances 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.79
    Grade
    -0.70
    00200000
    -0.68
    Guard
    -0.67
    jamin
    -0.67
    Downloadha
    -0.66
    trak
    -0.65
    vez
    -0.65
    culosis
    -0.64
    Adv
    -0.64
    POSITIVE LOGITS
     split
    1.08
    Split
    1.06
     splits
    0.95
    split
    0.93
     SPL
    0.89
    ters
    0.86
     Split
    0.86
     splitting
    0.81
     peas
    0.75
    paralle
    0.74
    Activations Density 0.008%

    No Known Activations