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. 29393
    Prev
    Next
    INDEX
    Explanations

    elements related to web design and development

    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
    419
    +0.21
    1.2%
    507
    +0.18
    1.0%
    127
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.21
    0.10
    507
    +0.18
    0.04
    377
    +0.11
    0.08
    Negative Logits
    Ļª
    -3.31
    ©
    -3.05
    §
    -2.86
    ģ
    -2.83
    ª
    -2.77
    Į
    -2.76
    Ģ
    -2.75
    ¯
    -2.74
    ŀ
    -2.67
    ĸ
    -2.66
    POSITIVE LOGITS
    posed
    1.45
     causality
    1.36
    rolled
    1.29
     quo
    1.26
    buffered
    1.26
    theless
    1.25
    fried
    1.24
     Reduction
    1.23
    wind
    1.22
    usual
    1.21
    Activations Density 4.005%

    No Known Activations