© 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. 1-RES-JB
    11. 14382
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing things or experiences

    oai_token-act-pair · gpt-3.5-turbo

    the word "wonderful."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avis
    -0.90
    PD
    -0.83
    iph
    -0.80
    pper
    -0.79
    unker
    -0.73
    arers
    -0.72
    bots
    -0.72
    consumer
    -0.71
    idel
    -0.71
    lay
    -0.70
    POSITIVE LOGITS
     wonderful
    0.91
    terday
    0.89
     Wonderful
    0.80
     joy
    0.76
    astically
    0.75
     surprises
    0.75
     gracious
    0.75
     amazing
    0.75
    NESS
    0.73
     sounding
    0.72
    Activations Density 0.012%

    No Known Activations