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. 7-RES-JB
    6. 21016
    Prev
    Next
    INDEX
    Explanations

    dates and times written in the format of numbers with periods between them

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidel
    -0.78
     stre
    -0.67
    £ı
    -0.65
     shroud
    -0.64
    idence
    -0.63
    uracy
    -0.63
     comparisons
    -0.62
     deceptive
    -0.62
     trouble
    -0.62
     association
    -0.61
    POSITIVE LOGITS
    000
    1.04
    05
    0.99
    07
    0.97
    06
    0.96
    09
    0.95
    5
    0.94
    500
    0.94
    04
    0.94
    08
    0.91
    00
    0.91
    Activations Density 0.122%

    No Known Activations