© 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. 8-RES-JB
    11. 24062
    Prev
    Next
    INDEX
    Explanations

    phrases related to downloading software or files

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "download" and associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otics
    -0.70
    obic
    -0.67
    heastern
    -0.66
     funer
    -0.66
    ousy
    -0.65
    otic
    -0.64
    ollar
    -0.64
    oking
    -0.62
    rimination
    -0.62
    Ń·
    -0.61
    POSITIVE LOGITS
    DragonMagazine
    1.10
     CSV
    1.05
     file
    1.02
     files
    0.99
     pdf
    0.97
     downloaded
    0.97
     firmware
    0.96
     ZIP
    0.95
     File
    0.94
     PDF
    0.92
    Activations Density 0.189%

    No Known Activations