© 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. 3-RES-JB
    11. 23272
    Prev
    Next
    INDEX
    Explanations

    phrases related to celebrations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "celebrate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iban
    -0.70
     sucked
    -0.68
    nih
    -0.66
    co
    -0.64
     leak
    -0.62
     pistols
    -0.62
     drawer
    -0.62
    abases
    -0.62
     pretext
    -0.60
     reservoir
    -0.60
    POSITIVE LOGITS
     celebrating
    1.03
     celebrations
    1.00
     Celebr
    0.91
    brate
    0.88
    âĿ
    0.88
     holidays
    0.82
     celebration
    0.82
     celebrates
    0.81
     celebrate
    0.79
    nesday
    0.79
    Activations Density 0.022%

    No Known Activations