© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5740
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Xiaomi"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of technology companies and surveillance systems

    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
    zee
    -0.91
    ãĤ©
    -0.86
    ultimate
    -0.85
    inges
    -0.80
    itial
    -0.76
    izens
    -0.76
    fell
    -0.75
    agram
    -0.75
    izontal
    -0.74
    apter
    -0.74
    POSITIVE LOGITS
     millenn
    0.88
    ulously
    0.74
     carriage
    0.69
     corrid
    0.67
    oing
    0.66
    ourgeois
    0.66
     unchecked
    0.64
     clearance
    0.63
    âĹ¼
    0.62
     Leone
    0.62
    Activations Density 0.033%

    No Known Activations