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. 5731
    Prev
    Next
    INDEX
    Explanations

    actions related to surveillance and monitoring

    oai_token-act-pair · gpt-3.5-turbo

    references to surveillance and monitoring activities

    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
    urai
    -0.77
    iji
    -0.72
    ingu
    -0.69
    igham
    -0.68
     comprom
    -0.68
     cliché
    -0.66
    nyder
    -0.65
     rhet
    -0.64
    oiler
    -0.64
    uphem
    -0.63
    POSITIVE LOGITS
     whereabouts
    1.07
     workings
    0.78
     transmissions
    0.75
     sightings
    0.73
    tnc
    0.72
     unseen
    0.71
     tracks
    0.71
     footprints
    0.70
     elapsed
    0.70
     tid
    0.70
    Activations Density 0.867%

    No Known Activations