© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    adverbs that intensify the emotional or descriptive nature of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deeply" suggesting strong emotional states or reactions

    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
    ulia
    -0.84
     Citation
    -0.79
    pez
    -0.69
    pload
    -0.69
    yip
    -0.68
     Parenthood
    -0.68
    amins
    -0.67
    ifully
    -0.65
    anwhile
    -0.65
    iture
    -0.63
    POSITIVE LOGITS
     ingrained
    1.07
     rooted
    1.00
     saddened
    0.92
     implicated
    0.88
     flawed
    0.88
     connected
    0.87
     intertwined
    0.87
     wounded
    0.84
     offended
    0.84
     engaged
    0.84
    Activations Density 0.035%

    No Known Activations