© 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. 7-RES-JB
    11. 12609
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or roles played by subjects, particularly in the context of legal or moral implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cum
    -0.70
     Topics
    -0.68
     Gloss
    -0.66
     Thrust
    -0.64
    arnaev
    -0.63
     Shards
    -0.63
     Celebr
    -0.60
     topics
    -0.60
    ribes
    -0.60
     Recipes
    -0.59
    POSITIVE LOGITS
     opposite
    0.77
     differently
    0.76
     behalf
    0.72
     unilaterally
    0.69
    RECT
    0.68
    uously
    0.68
    ively
    0.67
     veto
    0.67
     instinct
    0.66
     inverse
    0.65
    Activations Density 0.105%

    No Known Activations