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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29575
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and attorney responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    346
    +0.17
    1.0%
    339
    +0.15
    0.9%
    198
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.17
    0.07
    2
    +0.15
    0.14
    346
    +0.13
    0.10
    Negative Logits
    ĨĴ
    -2.70
    IJ
    -2.69
    Ĺ
    -2.59
    ĻĤ
    -2.58
    Ĥ¬
    -2.41
    Ļª
    -2.41
    Ĩ
    -2.29
    ļ
    -2.28
    ³
    -2.26
    Ī
    -2.21
    POSITIVE LOGITS
    ilities
    1.57
     lasted
    1.48
    ).[
    1.48
    VERS
    1.46
     jud
    1.45
     knowledgeable
    1.41
     agrees
    1.40
    holds
    1.39
    included
    1.39
     lasts
    1.39
    Activations Density 6.392%

    No Known Activations