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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5647
    Prev
    Next
    INDEX
    Explanations

    RSS feeds to subscribe to

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of "feeds," particularly in digital or social media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.71
     Templar
    -0.69
     Vanilla
    -0.67
    orney
    -0.66
    uman
    -0.64
    oha
    -0.63
    女
    -0.63
     Spectre
    -0.62
    uin
    -0.61
    clinton
    -0.61
    POSITIVE LOGITS
     feed
    3.85
     feeds
    2.93
     Feed
    2.80
    feed
    2.68
    Feed
    2.16
     feeding
    2.14
     fed
    1.80
    feeding
    1.56
    fed
    1.31
     eat
    1.18
    Activations Density 0.024%

    No Known Activations