© 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. 3-RES-JB
    11. 3897
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'conscience'

    oai_token-act-pair · gpt-3.5-turbo

    references to moral or ethical principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olds
    -0.69
     Extended
    -0.68
    ORPG
    -0.66
     Kinnikuman
    -0.66
    eri
    -0.65
    gars
    -0.64
     Vehicles
    -0.61
    ten
    -0.59
     Sit
    -0.59
    ramid
    -0.57
    POSITIVE LOGITS
     conscience
    1.05
    fulness
    0.81
     awareness
    0.80
     consciousness
    0.74
     compass
    0.74
    ful
    0.71
    EngineDebug
    0.69
    cipled
    0.69
     curiosity
    0.67
     detector
    0.67
    Activations Density 0.005%

    No Known Activations