© 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. 11910
    Prev
    Next
    INDEX
    Explanations

    references to cybersecurity and potential threats or attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to adversaries and foes in a competitive or conflict context

    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
     Lama
    -0.95
    itialized
    -0.76
    rophe
    -0.75
    regon
    -0.73
    lander
    -0.72
    umn
    -0.70
    ordered
    -0.70
    cus
    -0.69
    ivan
    -0.69
    urgy
    -0.68
    POSITIVE LOGITS
     adversaries
    1.09
     foe
    0.96
     adversary
    0.95
     foes
    0.94
     opponents
    0.87
     challeng
    0.84
     vanquished
    0.80
     advers
    0.79
    nces
    0.78
     opponent
    0.77
    Activations Density 0.024%

    No Known Activations