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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5865
    Prev
    Next
    INDEX
    Explanations

    various mentions of the word "selection", both simple and in specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "selection."

    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
    peria
    -0.77
    kos
    -0.76
    wig
    -0.72
    mond
    -0.67
    pton
    -0.65
    hur
    -0.64
    alone
    -0.63
    FORMATION
    -0.61
    ned
    -0.61
    aths
    -0.61
    POSITIVE LOGITS
    selection
    1.13
     criteria
    0.91
     selection
    0.88
     Selection
    0.84
    ivity
    0.82
     selections
    0.81
    eering
    0.79
    axe
    0.78
    azy
    0.77
    ively
    0.76
    Activations Density 0.021%

    No Known Activations