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. 11687
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and associated formatting elements in code snippets

    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
    423
    +0.13
    0.7%
    320
    +0.11
    0.6%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.13
    0.07
    431
    +0.11
    0.06
    374
    +0.10
    0.05
    Negative Logits
    ichi
    -1.70
     streets
    -1.48
     costs
    -1.44
     alike
    -1.44
    izo
    -1.44
     criticism
    -1.42
    ji
    -1.40
    escence
    -1.39
    ocene
    -1.37
    ise
    -1.37
    POSITIVE LOGITS
    ¢
    4.29
    Īĺ
    4.29
    °
    3.90
    ¯
    3.87
    ¦
    3.85
    ¿
    3.80
    ¾
    3.77
    ¿½
    3.67
    ¬
    3.64
    ·¸
    3.54
    Activations Density 0.771%

    No Known Activations