© 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. 16415
    Prev
    Next
    INDEX
    Explanations

    references to the Tor network

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Tor network and its related elements

    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
    ãħĭ
    -0.71
    draft
    -0.70
    heid
    -0.70
    ership
    -0.69
    holder
    -0.69
     [&
    -0.67
     Dakota
    -0.67
    ãģį
    -0.66
    tenance
    -0.66
    stakes
    -0.66
    POSITIVE LOGITS
    onto
    0.92
    mented
    0.92
    rington
    0.86
    rance
    0.86
    reon
    0.82
    sten
    0.81
    ricia
    0.81
    rent
    0.79
    pora
    0.76
    adal
    0.76
    Activations Density 0.006%

    No Known Activations