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. 17048
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "Mandelt" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'Mandelbrot' and related terms associated with the Mandelbrot set

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    iners
    -0.79
    nings
    -0.76
     metabol
    -0.76
     reload
    -0.73
    cius
    -0.69
    ither
    -0.69
    runners
    -0.67
     catching
    -0.67
    runner
    -0.64
    tics
    -0.64
    POSITIVE LOGITS
     Mand
    4.11
    Mand
    2.64
     mand
    2.28
    mand
    1.68
     Mant
    1.39
     mandate
    1.32
     Kab
    1.17
     Mandal
    1.10
     Mandatory
    1.10
     Kund
    1.09
    Activations Density 0.013%

    No Known Activations