© 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. 10-RES-JB
    11. 7786
    Prev
    Next
    INDEX
    Explanations

    mentions of actions and events happening sequentially

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itational
    -0.74
    ãĤ´ãĥ³
    -0.73
    icter
    -0.73
    1001
    -0.67
    GY
    -0.66
    hill
    -0.65
    shift
    -0.65
    asse
    -0.64
    ocaly
    -0.64
    reshold
    -0.64
    POSITIVE LOGITS
     furthermore
    1.35
     moreover
    1.33
     consequently
    1.32
     therefore
    1.21
     rightfully
    1.14
     hence
    1.11
     thus
    1.11
     although
    1.10
     indeed
    1.09
     secondly
    1.05
    Activations Density 0.272%

    No Known Activations