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. 1308
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving updates and special offers

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to receiving updates or notifications

    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
    verning
    -0.85
    avery
    -0.79
    tein
    -0.77
    odor
    -0.76
    eur
    -0.75
    rifice
    -0.75
    gha
    -0.72
    zh
    -0.71
    iac
    -0.70
    nered
    -0.70
    POSITIVE LOGITS
     notifications
    0.95
     updates
    0.95
     Updates
    0.88
     update
    0.85
     notification
    0.82
    ilver
    0.80
     alerts
    0.80
    mith
    0.73
     Notification
    0.73
     announcements
    0.73
    Activations Density 0.017%

    No Known Activations