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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 6953
    Prev
    Next
    INDEX
    Explanations

    words related to days of the week and activities/events occurring on those days

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms related to time or events

    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
    alties
    -0.79
    ographically
    -0.72
    wit
    -0.72
    then
    -0.71
    washed
    -0.70
    rust
    -0.69
    vae
    -0.67
    avering
    -0.67
    heit
    -0.67
    don
    -0.67
    POSITIVE LOGITS
     announcement
    0.89
     morning
    0.82
     arrival
    0.81
     deadline
    0.80
     edition
    0.77
     afternoon
    0.76
     biggest
    0.74
     anniversary
    0.74
     unveiling
    0.73
     evening
    0.72
    Activations Density 0.038%

    No Known Activations