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. 9-RES-JB
    6. 2194
    Prev
    Next
    INDEX
    Explanations

    phrases related to time

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hens
    -0.70
    untu
    -0.56
    bench
    -0.56
    gow
    -0.55
    mar
    -0.55
    ifts
    -0.55
    elected
    -0.54
    liquid
    -0.53
    lett
    -0.53
    ose
    -0.53
    POSITIVE LOGITS
     same
    0.99
     phenomenon
    0.98
     latter
    0.94
     topic
    0.86
    .<
    0.78
    .[
    0.78
     trope
    0.78
     matter
    0.77
    FTWARE
    0.77
    MSN
    0.75
    Activations Density 1.036%

    No Known Activations