© 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. 10-RES-JB
    11. 10464
    Prev
    Next
    INDEX
    Explanations

    phrases related to keeping a watchful eye on something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to vigilance or monitoring

    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
    atro
    -0.66
     displ
    -0.64
     differed
    -0.59
     minus
    -0.59
    codes
    -0.59
    adj
    -0.57
    \/\/
    -0.57
    via
    -0.56
    Sov
    -0.56
    VAL
    -0.55
    POSITIVE LOGITS
     peeled
    1.15
     eye
    0.92
     vigil
    0.85
     tuned
    0.82
     lookout
    0.80
     glued
    0.80
    watch
    0.75
     watch
    0.75
    eful
    0.75
     Eye
    0.74
    Activations Density 0.045%

    No Known Activations