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. 1-RES-JB
    6. 24377
    Prev
    Next
    INDEX
    Explanations

    numeric sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to statistics or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugal
    -0.77
    elong
    -0.74
    inals
    -0.70
    allo
    -0.68
    coat
    -0.67
    ebin
    -0.67
    inges
    -0.67
    ggies
    -0.66
    emade
    -0.65
    etts
    -0.65
    POSITIVE LOGITS
    6666
    1.08
    571
    0.95
    597
    0.90
    OPLE
    0.89
    576
    0.87
    688
    0.87
    446
    0.85
    448
    0.85
    779
    0.85
    678
    0.85
    Activations Density 0.038%

    No Known Activations