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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 8605
    Prev
    Next
    INDEX
    Explanations

    terms related to android development commands

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Android development paths and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jasper
    -0.75
     Norris
    -0.74
    CLASSIFIED
    -0.74
     Furious
    -0.71
     Horowitz
    -0.70
     Dys
    -0.70
     Coil
    -0.69
    ÃĥÃĤ
    -0.67
     Yaz
    -0.67
     Rounds
    -0.66
    POSITIVE LOGITS
    sama
    1.11
    san
    1.05
    events
    1.05
    utils
    1.01
    style
    1.00
    server
    0.95
    spl
    0.95
    type
    0.94
    project
    0.93
    info
    0.92
    Activations Density 0.068%

    No Known Activations