Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14046
    Prev
    Next
    INDEX
    Explanations

    instances where an action or event is being described as the first time it has occurred

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "when I first" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.75
     Vish
    -0.69
     Brah
    -0.67
    RAM
    -0.66
     Rodrigo
    -0.64
    asty
    -0.63
    crim
    -0.62
     Gould
    -0.62
     à¤
    -0.62
    oute
    -0.61
    POSITIVE LOGITS
     responders
    1.03
     baseman
    0.99
     glance
    0.96
     blush
    0.86
     glim
    0.80
     lady
    0.78
    arily
    0.76
     estab
    0.75
     embark
    0.75
     encount
    0.74
    Activations Density 0.027%

    No Known Activations