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. 5-RES-JB
    6. 10788
    Prev
    Next
    INDEX
    Explanations

    individual nouns or noun phrases that contain the word "of"

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.76
     CBI
    -0.62
     ss
    -0.61
     cf
    -0.61
     prices
    -0.61
     barg
    -0.60
     passers
    -0.60
     galleries
    -0.59
     scores
    -0.59
     appra
    -0.59
    POSITIVE LOGITS
    rontal
    1.33
    sky
    1.00
    uture
    0.96
    eatures
    0.95
    ortunately
    0.93
    unction
    0.92
    icial
    0.92
    rost
    0.88
    rame
    0.87
     course
    0.87
    Activations Density 0.027%

    No Known Activations