© 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. 1-RES-JB
    11. 3356
    Prev
    Next
    INDEX
    Explanations

    specific computer-related folders and file extensions

    oai_token-act-pair · gpt-3.5-turbo

    references to folders and folder structures in a computer context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emic
    -0.75
    ody
    -0.66
    acon
    -0.64
    vati
    -0.63
    ingo
    -0.62
    omon
    -0.62
     Acts
    -0.61
     Jud
    -0.60
    ofi
    -0.59
    uca
    -0.59
    POSITIVE LOGITS
     folder
    1.24
     Folder
    1.18
     folders
    1.10
    folder
    1.09
     drawer
    0.93
    ãĤ¼ãĤ¦ãĤ¹
    0.91
    Folder
    0.90
    files
    0.81
    intosh
    0.80
    washer
    0.78
    Activations Density 0.011%

    No Known Activations