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. 20628
    Prev
    Next
    INDEX
    Explanations

    dates in the format of a day followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the date "17" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Dates in the format of a day followed by a number

    Explanation Uploaded by User
    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
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    ר
    -0.72
    tc
    -0.67
    rency
    -0.67
    elope
    -0.64
     conduc
    -0.64
    idi
    -0.64
    ippy
    -0.64
     sprinkled
    -0.61
    .""
    -0.60
     patience
    -0.58
    POSITIVE LOGITS
     17
    2.80
     16
    1.99
     18
    1.95
     19
    1.94
    17
    1.91
     1700
    1.81
     23
    1.77
     27
    1.76
     13
    1.76
     21
    1.70
    Activations Density 0.047%

    No Known Activations