© 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. 6-RES-JB
    11. 11937
    Prev
    Next
    INDEX
    Explanations

    phrases related to secrecy and hidden information

    oai_token-act-pair · gpt-3.5-turbo

    references to secrecy and confidentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.68
    orio
    -0.63
    assadors
    -0.61
    aurus
    -0.60
    nesota
    -0.60
    chance
    -0.59
    idth
    -0.59
    omaly
    -0.58
    minster
    -0.57
     stiffness
    -0.56
    POSITIVE LOGITS
    isSpecialOrderable
    0.96
     until
    0.95
     till
    0.86
     unless
    0.85
     lest
    0.83
    ariat
    0.79
    displayText
    0.78
     anymore
    0.76
     indefinitely
    0.75
     publicly
    0.74
    Activations Density 0.125%

    No Known Activations