© 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. 8-RES-JB
    11. 3876
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of understanding or comprehension is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the concept of understanding

    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
    onies
    -0.84
    onto
    -0.73
    hire
    -0.72
    boro
    -0.71
    \/\/
    -0.66
    quet
    -0.65
    adier
    -0.65
    inating
    -0.65
    onte
    -0.64
    picking
    -0.64
    POSITIVE LOGITS
     WHY
    1.07
     why
    1.07
     how
    0.98
    ably
    0.95
    why
    0.86
     comprehension
    0.82
     Understanding
    0.81
     Understand
    0.79
     whats
    0.77
    ingly
    0.77
    Activations Density 0.047%

    No Known Activations