© 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. 23845
    Prev
    Next
    INDEX
    Explanations

    directory names and paths within a computing context

    oai_token-act-pair · gpt-3.5-turbo

    references to directories and file structures

    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
    acting
    -0.79
    acted
    -0.77
    pter
    -0.76
    Ò
    -0.73
    rained
    -0.71
    akening
    -0.70
    acial
    -0.66
    emic
    -0.65
    auntlets
    -0.65
    psey
    -0.65
    POSITIVE LOGITS
     Contents
    0.94
     directory
    0.94
     folders
    0.91
     folder
    0.90
     '/
    0.89
     directories
    0.89
     "/
    0.87
     descriptor
    0.87
    =/
    0.86
    ystem
    0.86
    Activations Density 0.038%

    No Known Activations