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. 14311
    Prev
    Next
    INDEX
    Explanations

    commands or references related to changing directories in a programming or development context, such as "cd" commands

    oai_token-act-pair · gpt-3.5-turbo

    commands related to directory navigation in a file system

    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
    ipeg
    -0.76
     absor
    -0.75
    gren
    -0.70
    bringer
    -0.64
    Grade
    -0.63
     Hels
    -0.62
    IFA
    -0.62
     Gors
    -0.62
    zzo
    -0.61
    assisted
    -0.61
    POSITIVE LOGITS
    oche
    0.88
     cd
    0.87
    artment
    0.78
    aniel
    0.77
    udi
    0.76
    ouble
    0.75
    ython
    0.73
    cd
    0.72
    onga
    0.72
    elta
    0.70
    Activations Density 0.029%

    No Known Activations