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. 10-RES-JB
    6. 15617
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "First,"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "First" in relation to an introduction or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.66
    rams
    -0.66
     ranges
    -0.61
    Wed
    -0.60
    âĹ¼
    -0.59
    ļéĨĴ
    -0.58
    nz
    -0.57
    etheless
    -0.57
     persisted
    -0.56
    vell
    -0.56
    POSITIVE LOGITS
     introdu
    0.95
     congratulations
    0.94
     let
    0.94
     congr
    0.89
    ibaba
    0.85
     initialize
    0.82
     Introduction
    0.82
     apologize
    0.80
     acknowledge
    0.80
     lets
    0.77
    Activations Density 0.107%

    No Known Activations