© 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. 1-RES-JB
    11. 24310
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that express dependency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating dependency or condition

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vision
    -0.80
    nels
    -0.79
    mary
    -0.68
    atur
    -0.67
    lis
    -0.67
    cap
    -0.65
    vis
    -0.65
    nings
    -0.64
    jc
    -0.64
     Pall
    -0.64
    POSITIVE LOGITS
     depended
    1.15
     depends
    0.98
     challeng
    0.97
    ¬¼
    0.91
     depend
    0.90
     adversely
    0.84
    ratulations
    0.84
     confir
    0.84
     ende
    0.83
    awaru
    0.80
    Activations Density 0.011%

    No Known Activations