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. 8-RES-JB
    6. 23093
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or events happening during a particular time or period, possibly in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events and activities occurring during specific time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wiser
    -0.72
    NAME
    -0.62
     Genie
    -0.61
    ById
    -0.61
     Shares
    -0.60
    enance
    -0.59
    ANI
    -0.58
     guessed
    -0.58
    ,,,,,,,,
    -0.57
     laure
    -0.57
    POSITIVE LOGITS
     period
    1.02
     periods
    0.95
     lull
    0.91
     trials
    0.90
     recess
    0.90
     holidays
    0.89
    hunt
    0.88
     sessions
    0.87
    imester
    0.87
     festivities
    0.86
    Activations Density 0.255%

    No Known Activations