© 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. 4-RES-JB
    6. 4442
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in sentences expressing different viewpoints or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

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

    No Comments

    Negative Logits
    uta
    -0.76
    ut
    -0.71
    Times
    -0.66
    agon
    -0.65
    1001
    -0.64
    NVIDIA
    -0.64
    ji
    -0.63
     Powered
    -0.63
    DX
    -0.62
    levant
    -0.62
    POSITIVE LOGITS
     furthermore
    1.16
     consequently
    1.16
     therefore
    1.14
     moreover
    1.10
     secondly
    1.04
     hence
    1.00
     thence
    0.98
     then
    0.97
     thus
    0.96
     preferably
    0.95
    Activations Density 0.288%

    No Known Activations