Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3014
    Prev
    Next
    INDEX
    Explanations

    keywords related to contexts or entities with the name "Joy" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Joy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anguage
    -0.73
    arians
    -0.73
    ngth
    -0.72
    oug
    -0.70
    hetically
    -0.67
    è¦ļéĨĴ
    -0.66
     Adamant
    -0.65
    omething
    -0.65
     thirds
    -0.64
     blockers
    -0.63
    POSITIVE LOGITS
    stick
    1.08
    sticks
    1.01
    lyn
    0.99
    cean
    0.94
     Joy
    0.87
    cy
    0.80
    ners
    0.78
    ously
    0.78
    elia
    0.77
    bal
    0.74
    Activations Density 0.028%

    No Known Activations