© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 4297
    Prev
    Next
    INDEX
    Explanations

    people looking into each other's eyes

    oai_token-act-pair · gpt-3.5-turbo

    instances of looking at or making eye contact with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥİ
    -0.69
    atra
    -0.67
     ASC
    -0.65
    avier
    -0.65
    ¬¼
    -0.64
    olo
    -0.63
    Fact
    -0.62
    eno
    -0.61
     orchestr
    -0.60
    ulo
    -0.60
    POSITIVE LOGITS
     blank
    1.06
     curiously
    1.01
     disappro
    1.00
     puzzled
    0.98
     horrified
    0.94
     stares
    0.94
     quizz
    0.92
     eyes
    0.90
     frown
    0.90
     suspicious
    0.89
    Activations Density 0.152%

    No Known Activations