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

    Neuronpedia

    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. 1-RES-JB
    11. 23145
    Prev
    Next
    INDEX
    Explanations

    phrases related to enforcement agencies or specialized task forces

    oai_token-act-pair · gpt-3.5-turbo

    references to various task forces or organized groups related to law enforcement or crime prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sclerosis
    -0.77
    utics
    -0.69
     pes
    -0.69
    wcs
    -0.66
     redemption
    -0.64
     immersion
    -0.64
     xen
    -0.62
     polarized
    -0.61
    mph
    -0.61
    Champ
    -0.60
    POSITIVE LOGITS
     Task
    1.36
    Task
    0.99
    task
    0.89
    Queue
    0.80
     Suit
    0.78
     Sched
    0.76
    abus
    0.75
     Sheet
    0.73
    master
    0.73
     Forces
    0.73
    Activations Density 0.011%

    No Known Activations