© 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. 17773
    Prev
    Next
    INDEX
    Explanations

    phrases related to monitoring or keeping watch on something

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around monitoring and vigilance

    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
     Dimensions
    -0.68
    Motor
    -0.66
    !/
    -0.66
    mes
    -0.66
     directions
    -0.65
    ode
    -0.64
    ODE
    -0.63
    storms
    -0.62
    IDS
    -0.62
    asions
    -0.61
    POSITIVE LOGITS
     vigil
    0.96
    hold
    0.92
     lid
    0.91
     foothold
    0.85
    icum
    0.84
     sizeable
    0.83
     lookout
    0.82
     handful
    0.82
     secret
    0.80
     record
    0.78
    Activations Density 0.101%

    No Known Activations