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. 9591
    Prev
    Next
    INDEX
    Explanations

    descriptions indicating a level of quality or extent

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fairly" indicating a moderate or measured tone

    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
    STER
    -0.73
     Extensions
    -0.66
    inis
    -0.66
     Landing
    -0.66
     Tao
    -0.64
    ipper
    -0.64
    RY
    -0.63
    aer
    -0.62
     Plans
    -0.62
     Archives
    -0.61
    POSITIVE LOGITS
    itably
    0.98
     manageable
    0.86
     fair
    0.85
     fairly
    0.83
     accurate
    0.82
    ensical
    0.82
     readable
    0.79
     harmless
    0.78
    cipled
    0.77
     evenly
    0.77
    Activations Density 0.004%

    No Known Activations