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. 1-RES-JB
    6. 11112
    Prev
    Next
    INDEX
    Explanations

    phrases related to the collection of data or information

    oai_token-act-pair · gpt-3.5-turbo

    the noun "collect" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellen
    -0.78
    mo
    -0.65
    ned
    -0.64
    word
    -0.63
    pher
    -0.63
    mia
    -0.62
    ffe
    -0.61
     Centauri
    -0.60
     departure
    -0.59
    than
    -0.58
    POSITIVE LOGITS
    collect
    1.23
     collect
    1.12
     Collect
    1.11
     collects
    1.08
    Collect
    1.06
    ographs
    1.03
     collecting
    0.98
    ibles
    0.96
     collector
    0.92
     collected
    0.91
    Activations Density 0.012%

    No Known Activations