© 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. 4-RES-JB
    11. 20835
    Prev
    Next
    INDEX
    Explanations

    words related to quarantine and guarantee

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quarantine and vaccination policies

    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
    FUL
    -0.77
     MacArthur
    -0.67
    CHR
    -0.67
    ¿½
    -0.65
    CVE
    -0.62
    £ı
    -0.60
    GY
    -0.60
     incred
    -0.60
     fabrication
    -0.60
     comprehension
    -0.60
    POSITIVE LOGITS
    arant
    1.12
    ormal
    0.96
    ined
    0.94
    ulas
    0.92
    arding
    0.92
    ees
    0.90
    eed
    0.90
    inated
    0.88
    ula
    0.87
    inal
    0.86
    Activations Density 0.010%

    No Known Activations