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. 321
    Prev
    Next
    INDEX
    Explanations

    events or occasions taking place

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "take place."

    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
    ould
    -0.74
    ooks
    -0.71
    apo
    -0.71
     cutter
    -0.69
    rounder
    -0.67
    ipedia
    -0.66
    ritical
    -0.63
    ifted
    -0.63
    irk
    -0.63
    illard
    -0.63
    POSITIVE LOGITS
    Ò
    0.93
    âĹ¼
    0.76
    actionDate
    0.75
    NetMessage
    0.73
    Interstitial
    0.73
     concurrently
    0.70
     amidst
    0.68
    Ń·
    0.67
     ashore
    0.66
    DAQ
    0.66
    Activations Density 0.030%

    No Known Activations