© 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. 220
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize a specific point or detail within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    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
    rior
    -0.69
    cycles
    -0.67
    emis
    -0.67
    boards
    -0.66
    ysis
    -0.65
    english
    -0.63
    ãĥ¬
    -0.62
    ãĥĺ
    -0.62
    este
    -0.61
    ãĥĥ
    -0.60
    POSITIVE LOGITS
     fateful
    0.98
     same
    0.89
     pesky
    0.87
     latter
    0.77
     particular
    0.76
     aspect
    0.75
     portion
    0.72
    cher
    0.71
     elusive
    0.70
     aforementioned
    0.70
    Activations Density 0.276%

    No Known Activations