© 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. 16019
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or difficulties

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or challenges in situations

    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
     scrimmage
    -0.69
    ô
    -0.63
    Prosecut
    -0.62
     collabor
    -0.60
     Badge
    -0.59
    ulton
    -0.58
     costing
    -0.58
    RN
    -0.57
     unfinished
    -0.57
     stabilization
    -0.56
    POSITIVE LOGITS
     skeptical
    1.14
     intrigued
    1.04
     wary
    0.94
     appalled
    0.94
     puzzled
    0.93
     dismay
    0.93
     scept
    0.92
     apprehens
    0.92
     amazed
    0.91
     fooled
    0.90
    Activations Density 0.316%

    No Known Activations