© 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. 2-RES-JB
    11. 19464
    Prev
    Next
    INDEX
    Explanations

    terms related to surveillance techniques and information gathering

    oai_token-act-pair · gpt-3.5-turbo

    terms related 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mankind
    -0.77
    Urban
    -0.72
    birth
    -0.72
     Duchess
    -0.72
     Anthrop
    -0.70
    HY
    -0.69
     Human
    -0.68
     Dragons
    -0.67
     Vulcan
    -0.65
    gas
    -0.65
    POSITIVE LOGITS
     wiret
    1.14
    apped
    1.03
    apping
    1.01
    apper
    0.90
     eaves
    0.90
     ank
    0.89
    kefeller
    0.88
    appers
    0.83
     arrang
    0.83
    obook
    0.82
    Activations Density 0.011%

    No Known Activations