© 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. 4-RES-SM
    11. 12173
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or support

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    397
    +0.26
    1.5%
    21
    +0.16
    0.9%
    286
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.26
    0.04
    323
    +0.16
    0.04
    322
    +0.11
    0.04
    Negative Logits
    ¼
    -3.75
    Ļª
    -3.66
    ĥ
    -3.46
    ĩ
    -3.39
    Ĩ
    -3.38
    ij
    -3.35
    »¿
    -3.19
    ¯
    -3.13
    Ģ
    -3.13
    ¸
    -3.05
    POSITIVE LOGITS
     me
    2.49
    edly
    2.07
     please
    1.67
     clarify
    1.60
     debugging
    1.49
     diagnosing
    1.47
    ????
    1.45
    ers
    1.44
     myself
    1.43
     out
    1.42
    Activations Density 0.137%

    No Known Activations