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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8790
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity

    oai_token-act-pair · gpt-3.5-turbo

    references to cybersecurity and cyber threats

    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
    ++++++++++++++++
    -0.93
    ered
    -0.85
     Flav
    -0.73
    âĢ¢âĢ¢
    -0.73
     LINE
    -0.70
    ELS
    -0.69
     Taste
    -0.67
    âķIJâķIJ
    -0.67
     Gomez
    -0.66
     Vie
    -0.66
    POSITIVE LOGITS
    netic
    1.31
    punk
    1.15
     cyber
    1.06
     espionage
    0.88
     hackers
    0.88
     hacker
    0.86
     Cyber
    0.84
     aggress
    0.84
    ategory
    0.84
     hacking
    0.84
    Activations Density 0.007%

    No Known Activations