© 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. 4-RES-JB
    11. 11042
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Gad" with varying degrees of relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gad" as well as variations of the word "Gand"

    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
    ŃĶ
    -0.77
    terday
    -0.75
     Purg
    -0.72
    ournal
    -0.71
    xual
    -0.69
    ĸļ
    -0.69
    į
    -0.65
    ģ«
    -0.64
    resents
    -0.63
    »Ĵ
    -0.63
    POSITIVE LOGITS
    gets
    1.08
     Gad
    1.01
    iants
    0.98
    artz
    0.88
    iant
    0.81
    rowth
    0.79
    ules
    0.78
    roid
    0.76
    gart
    0.76
    olin
    0.75
    Activations Density 0.008%

    No Known Activations