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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24213
    Prev
    Next
    INDEX
    Explanations

    phrases related to speed and efficiency

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating speed or efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLA
    -0.80
    uta
    -0.79
    YC
    -0.72
    ipel
    -0.72
    wcsstore
    -0.71
     Combine
    -0.71
    imated
    -0.70
    gard
    -0.69
    ĺħ
    -0.68
    orse
    -0.67
    POSITIVE LOGITS
     furious
    1.41
     dirty
    1.03
     decisive
    0.97
     efficient
    0.96
     steady
    0.95
    dirty
    0.94
     loose
    0.92
     efficiently
    0.89
     agile
    0.88
     furiously
    0.88
    Activations Density 0.069%

    No Known Activations