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. 16621
    Prev
    Next
    INDEX
    Explanations

    words related to connections or associations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "link" and its variations

    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
    sburg
    -0.78
    otos
    -0.69
    ZI
    -0.68
    ORK
    -0.67
     Penguins
    -0.65
     Nights
    -0.64
    oured
    -0.64
    ODUCT
    -0.63
    ccording
    -0.62
    »Ĵ
    -0.62
    POSITIVE LOGITS
    edin
    0.98
    link
    0.93
    chain
    0.91
    ages
    0.90
     connecting
    0.86
     linking
    0.86
     link
    0.86
     links
    0.83
    later
    0.82
     cables
    0.79
    Activations Density 0.036%

    No Known Activations