© 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. 7-RES-JB
    11. 12417
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'encryption'

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of encryption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gal
    -0.73
    llo
    -0.70
    arte
    -0.68
     Nau
    -0.66
     Starr
    -0.66
     Nichols
    -0.64
    ifact
    -0.64
     Kinn
    -0.63
    Leary
    -0.63
    anan
    -0.62
    POSITIVE LOGITS
    ryption
    1.36
     encryption
    1.21
     encrypt
    1.11
     encrypted
    1.07
    rypted
    1.07
     AES
    1.01
     cryptography
    0.96
     cryptographic
    0.92
     handshake
    0.90
    encrypted
    0.89
    Activations Density 0.044%

    No Known Activations