© 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. 7-RES-JB
    11. 2227
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the difficulty, surprise, or emotional response to a situation or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express varying degrees of difficulty or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SEN
    -0.69
    ceive
    -0.66
    face
    -0.62
     veh
    -0.62
     Nanto
    -0.62
    WN
    -0.62
     Generation
    -0.60
    ared
    -0.60
     coron
    -0.58
     Kris
    -0.57
    POSITIVE LOGITS
    ById
    0.96
    agascar
    0.80
     effic
    0.80
     objectionable
    0.78
     irresistible
    0.75
    AppData
    0.74
    bleacher
    0.74
    irlfriend
    0.74
     elusive
    0.71
     fertile
    0.70
    Activations Density 0.241%

    No Known Activations