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

    Neuronpedia

    Jacobian LensNEW
    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. 12651
    Prev
    Next
    INDEX
    Explanations

    terms related to the usefulness and appropriateness of practices or policies in various 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/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
    297
    +0.15
    0.9%
    503
    +0.12
    0.7%
    176
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.15
    0.09
    198
    +0.12
    0.10
    403
    +0.10
    0.04
    Negative Logits
    Īĺ
    -4.70
    ±
    -4.67
    Ĩ
    -4.58
    ·¸
    -4.49
    «
    -4.43
     ↵
    -4.40
    č↵
    -4.40
    -4.40
    -4.40
              ↵
    -4.40
    POSITIVE LOGITS
     considering
    2.57
     insofar
    2.49
     because
    2.48
     since
    2.36
     unless
    2.33
     if
    2.26
    ly
    2.25
     owing
    2.22
     for
    2.14
     given
    2.08
    Activations Density 0.716%

    No Known Activations