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. 0-RES-JB
    6. 20839
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Dat" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the term "Dat" and its variations, indicating a focus on data-related topics or entities

    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
     erection
    -0.79
     rebirth
    -0.72
    orman
    -0.68
     shepherd
    -0.68
     Armstrong
    -0.68
     laughter
    -0.67
     polish
    -0.67
     Albion
    -0.67
     springs
    -0.67
     bonding
    -0.66
    POSITIVE LOGITS
     Dat
    3.98
    Dat
    3.15
    dat
    2.79
     dat
    2.20
     dataset
    1.76
     datas
    1.74
     datasets
    1.60
     Data
    1.34
     Database
    1.18
     Tanz
    1.17
    Activations Density 0.036%

    No Known Activations