© 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. 13984
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and actions taken based on certain conditions or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "so" indicating conversational or narrative transitions

    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
    taboola
    -0.80
    BuyableInstoreAndOnline
    -0.71
    ocene
    -0.70
     acknow
    -0.66
    SpaceEngineers
    -0.66
     sidx
    -0.61
    qt
    -0.61
     Notice
    -0.59
    notice
    -0.59
    ortment
    -0.58
    POSITIVE LOGITS
     instead
    0.93
     we
    0.90
    instead
    0.79
     VICE
    0.77
    Instead
    0.72
     Leone
    0.72
     Instead
    0.71
    ruit
    0.70
     filmmakers
    0.70
     researchers
    0.68
    Activations Density 0.195%

    No Known Activations