Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15753
    Prev
    Next
    INDEX
    Explanations

    mentions of directories or folders in technical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to directories and folders in a filesystem context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emic
    -0.78
    egal
    -0.70
    pter
    -0.69
    acted
    -0.68
    Ò
    -0.66
    activ
    -0.65
    okin
    -0.64
    acting
    -0.63
    lev
    -0.63
     Pes
    -0.62
    POSITIVE LOGITS
     Folder
    1.04
     folder
    1.02
     folders
    0.98
    folder
    0.93
     contents
    0.83
    Folder
    0.81
    ystem
    0.80
     separ
    0.78
     drawer
    0.76
     (/
    0.76
    Activations Density 0.026%

    No Known Activations