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. 12170
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific organization or group named "Secular"

    oai_token-act-pair · gpt-3.5-turbo

    references to secular and humanist groups or contexts

    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
    lihood
    -0.85
     Warcraft
    -0.81
     GOODMAN
    -0.80
     Iris
    -0.72
    ãĥ£
    -0.70
    çİĭ
    -0.69
    è¦ļéĨĴ
    -0.69
    lifting
    -0.68
     Burnett
    -0.68
     Hearthstone
    -0.68
    POSITIVE LOGITS
    Sec
    1.10
     Sec
    1.05
    unia
    1.02
    ilege
    0.87
    recy
    0.85
    rets
    0.82
    ular
    0.82
    enture
    0.80
    marine
    0.80
    ession
    0.79
    Activations Density 0.009%

    No Known Activations