© 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. 11169
    Prev
    Next
    INDEX
    Explanations

    specific programming commands and structures related to configurations and details

    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
    17
    +0.20
    1.2%
    479
    +0.18
    1.0%
    332
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.20
    0.12
    135
    +0.18
    0.14
    17
    +0.14
    -0.01
    Negative Logits
    ¿½
    -2.28
    Ŀ
    -1.82
    ²
    -1.71
    ¨
    -1.58
    ncia
    -1.55
    Ľ
    -1.54
    ¹
    -1.52
    µ
    -1.49
    ¥
    -1.45
    ¸
    -1.41
    POSITIVE LOGITS
    ceived
    1.50
    icles
    1.49
    ied
    1.42
    ceiving
    1.42
     lands
    1.39
    isher
    1.35
    ental
    1.34
     recipient
    1.33
    ionale
    1.32
    ceiver
    1.31
    Activations Density 5.275%

    No Known Activations