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. 7416
    Prev
    Next
    INDEX
    Explanations

    words related to reminders

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote reminders or the act of reminding

    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
    efficients
    -0.71
    hair
    -0.70
    annis
    -0.68
    á
    -0.68
    estern
    -0.67
    inals
    -0.66
    ties
    -0.66
    quer
    -0.66
    mut
    -0.63
    tails
    -0.63
    POSITIVE LOGITS
     reminder
    1.22
     reminders
    1.22
     reminding
    0.92
     remind
    0.91
     vigilance
    0.73
     vigil
    0.71
     remembering
    0.71
    fulness
    0.70
     refreshed
    0.70
     glance
    0.69
    Activations Density 0.013%

    No Known Activations