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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4442
    Prev
    Next
    INDEX
    Explanations

    phrases related to welcoming or introductions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include welcoming messages and introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     implanted
    -0.77
    okia
    -0.73
    akable
    -0.72
     griev
    -0.71
     exerted
    -0.71
    conom
    -0.71
    ebted
    -0.70
    etooth
    -0.70
     hurled
    -0.69
     emitted
    -0.68
    POSITIVE LOGITS
     Subtle
    0.85
     Welcome
    0.74
     Paradise
    0.72
     Ask
    0.68
     Upper
    0.68
     Wonderland
    0.66
    ffee
    0.66
     STATS
    0.66
     Begin
    0.65
    elcome
    0.65
    Activations Density 0.071%

    No Known Activations