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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11947
    Prev
    Next
    INDEX
    Explanations

    references to monetary values and economic contexts

    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
    279
    +0.15
    0.9%
    313
    +0.14
    0.8%
    59
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.15
    0.03
    313
    +0.14
    0.02
    477
    +0.13
    0.03
    Negative Logits
    unnumbered
    -1.64
     assim
    -1.39
     itiner
    -1.39
    ión
    -1.36
     exhaustion
    -1.33
    cribe
    -1.31
     landmarks
    -1.30
     favor
    -1.29
     %{
    -1.28
     starvation
    -1.28
    POSITIVE LOGITS
    orld
    2.54
    ingly
    2.26
    ska
    2.20
    ritten
    2.11
    indow
    2.04
    riter
    2.01
    ledge
    1.97
    icz
    1.93
    itzer
    1.90
    ls
    1.87
    Activations Density 0.202%

    No Known Activations