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. 4-RES-JB
    6. 17763
    Prev
    Next
    INDEX
    Explanations

    instances where the term "paradigm" or "paradigm shift" appears

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to significant shifts in established frameworks or systems

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

    No Comments

    Negative Logits
    ionage
    -0.67
    hire
    -0.66
    gan
    -0.64
    bleacher
    -0.63
    llah
    -0.62
     Cheong
    -0.62
    erie
    -0.62
     Nationals
    -0.61
    ertodd
    -0.61
    idan
    -0.61
    POSITIVE LOGITS
     paradigm
    1.16
     parad
    1.03
    igmatic
    0.98
    igm
    0.84
     Parad
    0.78
     shift
    0.77
    norm
    0.73
    ĸļ
    0.70
     hegemony
    0.69
    ctr
    0.69
    Activations Density 0.011%

    No Known Activations