© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities or tasks

    oai_token-act-pair · gpt-3.5-turbo

    the word "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 @ 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
    uel
    -0.77
    cigarettes
    -0.72
    uba
    -0.71
    zan
    -0.70
    pell
    -0.70
    wic
    -0.68
    meric
    -0.67
    uty
    -0.67
    uts
    -0.67
    uta
    -0.67
    POSITIVE LOGITS
     thus
    1.00
     thereby
    0.93
     consequently
    0.93
     therefore
    0.92
     hence
    0.90
     subsequent
    0.88
     consequ
    0.85
     its
    0.85
     namesake
    0.83
     thence
    0.81
    Activations Density 0.274%

    No Known Activations