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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26957
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to scientific findings and processes

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    23
    +0.24
    1.4%
    478
    +0.16
    0.9%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.24
    0.03
    148
    +0.16
    0.03
    166
    +0.13
    0.04
    Negative Logits
    nem
    -1.53
    mage
    -1.48
     emergency
    -1.43
    plus
    -1.42
    ERC
    -1.41
    arter
    -1.39
    Plus
    -1.39
    starter
    -1.37
    rette
    -1.37
    illo
    -1.37
    POSITIVE LOGITS
    Ĥ
    2.27
    «
    2.25
    ĥ
    2.21
    ²
    2.11
    ¿½
    2.10
    ¿
    2.06
    Ŀ
    2.01
    akov
    2.00
    ¦
    1.94
    ¾
    1.94
    Activations Density 0.399%

    No Known Activations