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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4442
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Much of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that frequently start with "Much of" to discuss significant quantities or aspects of topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    opers
    -0.74
    perse
    -0.68
    士
    -0.68
    spir
    -0.68
    ħĭ
    -0.66
    dl
    -0.64
    pez
    -0.64
    otte
    -0.64
    ded
    -0.63
    eret
    -0.63
    POSITIVE LOGITS
     depends
    1.04
     hinges
    0.98
     happens
    0.93
     transpired
    0.88
     happened
    0.84
     depended
    0.84
     emphasis
    0.81
     importantly
    0.79
     occurs
    0.79
     ensued
    0.79
    Activations Density 0.096%

    No Known Activations