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. 24340
    Prev
    Next
    INDEX
    Explanations

    phrases related to SK (entity/keyword often repeated in the text)

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or group identified as "SK."

    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
     Mayweather
    -0.84
     Milton
    -0.70
     Manson
    -0.70
     Triangle
    -0.69
     Romero
    -0.68
     Kavanaugh
    -0.67
    ric
    -0.66
     Revenge
    -0.65
     Britann
    -0.65
     Hubbard
    -0.62
    POSITIVE LOGITS
    SK
    1.08
     SK
    1.05
    IRT
    0.92
    IPP
    0.89
    ull
    0.88
     mathemat
    0.87
     challeng
    0.82
    SEA
    0.81
    yrim
    0.81
    IES
    0.79
    Activations Density 0.005%

    No Known Activations