© 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. 1540
    Prev
    Next
    INDEX
    Explanations

    language related to privacy and data protection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to privacy and data protection

    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
    xual
    -0.80
    annis
    -0.71
    cki
    -0.67
    kell
    -0.67
    Production
    -0.66
    hani
    -0.64
    iatus
    -0.63
    mount
    -0.63
    eryl
    -0.62
    ensen
    -0.61
    POSITIVE LOGITS
     rights
    0.96
     protections
    0.93
     Rights
    0.91
     privacy
    0.90
     liberties
    0.81
     safeguards
    0.80
     Liberties
    0.77
     freedoms
    0.77
    rights
    0.75
    Privacy
    0.75
    Activations Density 0.025%

    No Known Activations