© 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. 11-RES-JB
    11. 1277
    Prev
    Next
    INDEX
    Explanations

    phrases related to weighing the pros and cons of a situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to evaluating pros and cons or making comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.82
    76561
    -0.80
    £ı
    -0.78
    æ©
    -0.73
    atha
    -0.73
    eday
    -0.71
    ģĸ
    -0.70
     laun
    -0.69
    cffffcc
    -0.67
    "]=>
    -0.65
    POSITIVE LOGITS
     drawbacks
    1.06
     detractors
    1.03
     disappro
    0.95
     disadvantages
    0.94
     disapproval
    0.92
     unfavorable
    0.91
     hinder
    0.91
     disadvantage
    0.89
     foes
    0.89
    Weak
    0.89
    Activations Density 0.256%

    No Known Activations