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. 0-RES-JB
    6. 17885
    Prev
    Next
    INDEX
    Explanations

    references to cultural aspects or the word "cultural."

    oai_token-act-pair · gpt-3.5-turbo

    references to cultural topics and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tracker
    -0.78
    rex
    -0.75
    rix
    -0.72
    fox
    -0.71
     Router
    -0.69
    atter
    -0.68
    eus
    -0.67
     Anon
    -0.66
     XT
    -0.66
     Prep
    -0.65
    POSITIVE LOGITS
     cultural
    3.27
     Cultural
    2.81
    cultural
    2.71
     culturally
    2.33
     culture
    2.02
    ultural
    1.98
    culture
    1.91
     Culture
    1.85
     multicultural
    1.78
     societal
    1.78
    Activations Density 0.017%

    No Known Activations