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. 10-RES-JB
    6. 4213
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious teachings and commandments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wow
    -0.72
    Lots
    -0.72
    CTV
    -0.72
    Plug
    -0.69
    ETS
    -0.68
    ãĥĩãĤ£
    -0.68
    CBC
    -0.67
     PST
    -0.67
    PDF
    -0.67
    NEWS
    -0.66
    POSITIVE LOGITS
     thou
    1.45
     thence
    1.30
    soever
    1.29
     hereafter
    1.15
     ye
    1.12
     Thou
    1.11
     moreover
    1.07
     doubtless
    1.06
     hath
    1.04
     hitherto
    1.03
    Activations Density 0.200%

    No Known Activations