© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20170
    Prev
    Next
    INDEX
    Explanations

    words related to things or experiences that are positive or delightful

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wonderful."

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

    No Comments

    Negative Logits
    ©¶æ
    -0.84
    arers
    -0.78
    avis
    -0.78
    pper
    -0.78
    PD
    -0.77
    gemony
    -0.77
    olate
    -0.77
    atum
    -0.74
    ppers
    -0.72
    opers
    -0.70
    POSITIVE LOGITS
     Samar
    0.77
     scenery
    0.75
     fortune
    0.74
     congratulations
    0.73
     gracious
    0.72
     joy
    0.70
    NESS
    0.70
     sounding
    0.70
     wonderful
    0.70
     opportunity
    0.69
    Activations Density 0.019%

    No Known Activations