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. 16654
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "against"

    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
    zel
    -0.82
    zl
    -0.79
    overed
    -0.78
    sonian
    -0.78
    psons
    -0.78
    INESS
    -0.77
    details
    -0.77
    oola
    -0.76
    jri
    -0.75
    chell
    -0.72
    POSITIVE LOGITS
     Samoa
    0.83
     opponents
    0.82
     foes
    0.76
     against
    0.75
     Ireland
    0.74
     opponent
    0.73
     Notre
    0.73
     gust
    0.72
     Syracuse
    0.69
     Cortex
    0.69
    Activations Density 0.033%

    No Known Activations