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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 19196
    Prev
    Next
    INDEX
    Explanations

    words related to development, growth, and progress

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "mat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Words that rhyme with flat

    No Comments

    Negative Logits
    éĹĺ
    -0.93
    ngth
    -0.71
    FUL
    -0.66
    velength
    -0.65
    vous
    -0.64
     condem
    -0.63
    IGH
    -0.63
    ãĤī
    -0.63
    æĸ¹
    -0.62
    FINE
    -0.60
    POSITIVE LOGITS
    hematically
    1.52
    rices
    1.38
    urity
    1.22
    hematic
    1.14
    hemat
    1.07
    ting
    1.07
    ilda
    1.03
    asonic
    0.98
    imes
    0.98
    het
    0.97
    Activations Density 0.014%

    No Known Activations