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. 8862
    Prev
    Next
    INDEX
    Explanations

    past experiences and personal history related to various activities and memories

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to personal experiences and memory

    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
    ansky
    -0.67
    othe
    -0.62
     Inspector
    -0.56
     Metropolitan
    -0.55
    tracking
    -0.55
     furious
    -0.54
     Cohn
    -0.54
     wary
    -0.54
     blame
    -0.53
     Chili
    -0.53
    POSITIVE LOGITS
     previous
    1.03
     beforehand
    0.89
     previously
    0.88
     prior
    0.87
     ago
    0.85
     earlier
    0.83
    ?".
    0.81
     ancestors
    0.78
     preceding
    0.78
    /-
    0.77
    Activations Density 0.834%

    No Known Activations