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. 4-RES-JB
    6. 23306
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases commonly known for a particular quality or association

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate known attributes or characteristics of a subject

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

    No Comments

    Negative Logits
    ieties
    -0.79
    ogether
    -0.76
    eros
    -0.71
    yden
    -0.66
    mare
    -0.66
    til
    -0.66
    urs
    -0.64
    orbit
    -0.64
    down
    -0.63
    ethyl
    -0.62
    POSITIVE LOGITS
    geries
    1.02
    gery
    0.94
    bidden
    0.88
    gotten
    0.85
    ked
    0.78
     awhile
    0.77
     centuries
    0.77
     instance
    0.74
     example
    0.73
    ays
    0.72
    Activations Density 0.123%

    No Known Activations