© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 10746
    Prev
    Next
    INDEX
    Explanations

    nutritional deficiencies in dietary surveys and related health impacts

    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
    320
    +0.24
    1.5%
    47
    +0.21
    1.3%
    271
    +0.20
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.24
    0.07
    47
    +0.21
    0.12
    320
    +0.20
    0.10
    Negative Logits
     audience
    -1.52
     Univ
    -1.49
    :**
    -1.41
    apest
    -1.39
     finishes
    -1.39
    erd
    -1.34
    ahoma
    -1.34
     ont
    -1.33
     ahead
    -1.31
    pshire
    -1.31
    POSITIVE LOGITS
    Īĺ
    2.87
    ¸
    2.59
    Ķ
    2.53
    ¿½
    2.52
     ↵
    2.42
    2.42
    ↵↵
    2.42
    2.42
    2.42
    2.42
    Activations Density 1.895%

    No Known Activations