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. 10-RES-JB
    6. 201
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods or historical events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts, often relating to time periods and milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raised
    -0.77
    perse
    -0.73
    ranked
    -0.73
    reau
    -0.71
    erers
    -0.69
    ertain
    -0.69
    bourg
    -0.69
    ply
    -0.69
    cipl
    -0.69
    xual
    -0.68
    POSITIVE LOGITS
     inception
    1.61
     beginning
    1.39
     onset
    1.34
     advent
    1.32
     outset
    1.30
     earliest
    1.21
     arrival
    1.20
     introduction
    1.18
     beginnings
    1.17
     1970
    1.16
    Activations Density 0.103%

    No Known Activations