© 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 EvalsExportsinterp-engineNEWAPI 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. 27752
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code snippets, particularly those involving warnings and error handling

    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
    186
    +0.17
    1.0%
    369
    +0.17
    1.0%
    156
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    387
    +0.17
    0.11
    291
    +0.17
    0.10
    497
    +0.15
    0.03
    Negative Logits
     Bund
    -1.54
    iously
    -1.51
    iert
    -1.48
     коÑĤоÑĢ
    -1.39
    athered
    -1.39
     another
    -1.38
     Lines
    -1.36
    elin
    -1.34
    rying
    -1.34
    ately
    -1.33
    POSITIVE LOGITS
    Ĥ¬
    2.46
    ĩ
    2.32
    Ĵ
    2.19
    ľĵ
    2.18
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.18
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.17
    »
    2.16
    ¶
    2.15
    ÃĥÃĤÃĥÃĤ
    2.12
    ģ
    2.12
    Activations Density 4.576%

    No Known Activations