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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 5804
    Prev
    Next
    INDEX
    Explanations

    text related to discussing holding law enforcement accountable

    oai_token-act-pair · gpt-3.5-turbo

    expressions of abstract or philosophical concepts related to existence and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frontline
    -0.92
     wallet
    -0.86
     freel
    -0.82
     wallets
    -0.81
     targeted
    -0.80
     streaming
    -0.80
     Marketplace
    -0.79
     thrott
    -0.78
     eligible
    -0.77
     registry
    -0.75
    POSITIVE LOGITS
    Thus
    1.38
    Chapter
    1.36
    CHAPTER
    1.29
    Therefore
    1.19
    THE
    1.14
    VII
    1.13
    References
    1.13
    Notes
    1.11
    Consider
    1.08
    Letter
    1.08
    Activations Density 0.367%

    No Known Activations