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. 14915
    Prev
    Next
    INDEX
    Explanations

    welcome messages or introductory phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include a welcoming expression or greeting

    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
    river
    -0.75
    negie
    -0.75
    appropri
    -0.71
    ariat
    -0.70
    rift
    -0.68
    nutrition
    -0.64
    orius
    -0.64
    arist
    -0.64
    suggest
    -0.63
    onel
    -0.63
    POSITIVE LOGITS
    giving
    0.92
    elcome
    0.89
     Welcome
    0.84
    prise
    0.84
    Welcome
    0.81
    ISTER
    0.78
     Guest
    0.73
     Surprise
    0.73
    prises
    0.72
    ISSION
    0.72
    Activations Density 0.013%

    No Known Activations