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

    Neuronpedia

    Jacobian LensNEW
    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. 22503
    Prev
    Next
    INDEX
    Explanations

    instances where the term "hacked" is mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hacked" and related terms about unauthorized access

    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
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.72
     Veter
    -0.69
    bu
    -0.67
    xus
    -0.67
     Starr
    -0.63
    BuyableInstoreAndOnline
    -0.62
     Liberia
    -0.62
    âĢ¢âĢ¢
    -0.61
    âĹ
    -0.61
    shr
    -0.61
    POSITIVE LOGITS
    intosh
    1.03
     hacking
    0.91
     hacked
    0.87
     hack
    0.84
    athon
    0.83
     hacks
    0.80
     hacker
    0.76
     hackers
    0.76
    driver
    0.73
    hent
    0.72
    Activations Density 0.012%

    No Known Activations