© 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. 8-RES-JB
    11. 2534
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or situations that are dependent on specific circumstances being met

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that include "as long as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.87
    MpServer
    -0.86
    esi
    -0.85
    ãĥĥãĥĪ
    -0.77
    Grade
    -0.74
    dale
    -0.73
    ãĥ¼ãĥĨ
    -0.72
    ´
    -0.72
    20439
    -0.72
    cffffcc
    -0.71
    POSITIVE LOGITS
     they
    0.87
     somebody
    0.80
     someone
    0.78
     survives
    0.77
     conditions
    0.73
     there
    0.73
     you
    0.72
     we
    0.71
     THEY
    0.71
     stays
    0.68
    Activations Density 0.048%

    No Known Activations