© 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. 4-RES-JB
    11. 16858
    Prev
    Next
    INDEX
    Explanations

    words related to encryption and security

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Enc," which likely relates to encryption or encoded content

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

    No Comments

    Negative Logits
    lift
    -0.72
    姫
    -0.71
    DAY
    -0.70
     Carnage
    -0.68
    giving
    -0.68
    geist
    -0.68
     Spice
    -0.68
    NOW
    -0.67
    sth
    -0.66
     Fernand
    -0.66
    POSITIVE LOGITS
    ryption
    1.42
    oded
    1.37
    rypted
    1.28
    oding
    1.27
    ounter
    1.22
    ounters
    1.19
    oder
    1.16
    rypt
    1.14
    ibel
    1.04
    ourage
    1.03
    Activations Density 0.014%

    No Known Activations