© 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. 2-RES-JB
    11. 355
    Prev
    Next
    INDEX
    Explanations

    the stem "stip," typically part of words related to "stipulations" or conditions

    oai_token-act-pair · gpt-4-turbo

    specific terms or phrases related to an official directive or requirement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contractual agreements or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.77
     Angry
    -0.74
     Randall
    -0.69
     Breath
    -0.66
     Tycoon
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.63
     Devon
    -0.63
     Roses
    -0.63
     Forrest
    -0.61
    =-=-=-=-=-=-=-=-
    -0.60
    POSITIVE LOGITS
     stip
    1.30
    endiary
    1.05
    ulum
    0.98
    ulates
    0.93
    abo
    0.91
    ulations
    0.91
    ula
    0.90
    ulation
    0.88
    ilit
    0.86
    ulated
    0.86
    Activations Density 0.011%

    No Known Activations