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. 3722
    Prev
    Next
    INDEX
    Explanations

    dates or locations mentioned in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    locations and events associated with leisure activities

    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
    naires
    -0.64
     decoration
    -0.62
     sten
    -0.61
     Ful
    -0.61
     automotive
    -0.60
     regular
    -0.60
     pupp
    -0.60
     mathemat
    -0.60
     Nib
    -0.60
     demonstr
    -0.59
    POSITIVE LOGITS
    Sensor
    0.94
    Status
    0.93
    Rating
    0.89
    Filename
    0.86
    Changes
    0.84
    Package
    0.84
    Price
    0.83
    Subject
    0.81
    Synopsis
    0.81
    Tags
    0.81
    Activations Density 0.258%

    No Known Activations