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. 7-RES-JB
    6. 5864
    Prev
    Next
    INDEX
    Explanations

    references to security or monitoring systems, such as surveillance cameras and radar equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surveillance and monitoring systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taxes
    -0.74
     appet
    -0.73
     Estate
    -0.73
    resents
    -0.72
     richest
    -0.72
    erenn
    -0.71
     finance
    -0.70
     broth
    -0.69
     Wealth
    -0.69
     Rebell
    -0.68
    POSITIVE LOGITS
     malfunction
    1.34
     detectors
    1.31
     transmit
    1.22
     detects
    1.15
     microphones
    1.09
     transmitting
    1.09
     monitors
    1.07
     devices
    1.07
     detector
    1.07
     sensors
    1.06
    Activations Density 0.584%

    No Known Activations