© 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. 11-RES-JB
    11. 1960
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of protecting or safeguarding

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to protection and safeguarding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imation
    -0.70
    argument
    -0.70
    pas
    -0.68
    achment
    -0.68
    ellen
    -0.66
     NEWS
    -0.66
    alter
    -0.65
    starter
    -0.65
    goo
    -0.63
    translation
    -0.62
    POSITIVE LOGITS
     against
    1.40
    against
    1.22
     Against
    1.06
    ively
    0.94
     innocent
    0.92
     sensitive
    0.90
     whistleblowers
    0.89
     ourselves
    0.89
     vulnerable
    0.89
     privacy
    0.88
    Activations Density 0.079%

    No Known Activations