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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 16781
    Prev
    Next
    INDEX
    Explanations

    entities that are in charge of overseeing or managing specific tasks or operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "oversee" and its variations in relation to control or supervision

    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
    ening
    -0.70
    False
    -0.67
    Secondly
    -0.62
    raid
    -0.61
    auld
    -0.60
    govtrack
    -0.60
     IMAGES
    -0.59
    filter
    -0.59
    bite
    -0.58
    NetMessage
    -0.58
    POSITIVE LOGITS
     overseeing
    1.23
     overseen
    0.94
     oversee
    0.91
     oversaw
    0.87
    orship
    0.79
     presided
    0.79
     oversees
    0.77
    stration
    0.75
    İĭ
    0.74
     superv
    0.70
    Activations Density 0.039%

    No Known Activations