© 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. 1-RES-SM
    11. 28030
    Prev
    Next
    INDEX
    Explanations

    SQL statements related to creating and managing database tables

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    16
    +0.13
    0.7%
    90
    +0.12
    0.7%
    26
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.13
    0.01
    165
    +0.12
    0.01
    157
    +0.12
    0.04
    Negative Logits
    º
    -2.51
    IJ
    -2.44
    ¾
    -2.28
    Ļª
    -2.27
    ij
    -2.23
    Ĩ
    -2.19
    »
    -2.18
    ¿½
    -2.17
      ↵
    -2.16
    -2.15
    POSITIVE LOGITS
     CIRCUIT
    1.83
    OUBLE
    1.51
     successor
    1.49
    ilion
    1.45
     figure
    1.44
    ERTY
    1.43
     predecessor
    1.40
    OLOR
    1.40
    bles
    1.39
     ordinal
    1.38
    Activations Density 0.440%

    No Known Activations