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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 20336
    Prev
    Next
    INDEX
    Explanations

    holiday greetings and well wishes

    oai_token-act-pair · gpt-3.5-turbo

    celebratory expressions and greetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     controversial
    -0.70
     laughable
    -0.68
     detecting
    -0.68
     installations
    -0.67
     underestimated
    -0.66
     documentaries
    -0.66
     analys
    -0.66
     difference
    -0.65
     contrasting
    -0.64
     jaw
    -0.64
    POSITIVE LOGITS
    ________________________________________________________________
    1.15
    END
    1.08
    Peace
    1.07
    ________________________________
    1.06
    âĻ¥
    1.06
    EDIT
    1.02
    ================================
    1.01
    ~~~~~~~~~~~~~~~~
    1.01
    ________________________
    1.01
    xxxxxxxx
    1.00
    Activations Density 0.271%

    No Known Activations