© 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. 2-RES-SM
    11. 30454
    Prev
    Next
    INDEX
    Explanations

    mention of free software and licensing terms

    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
    +0.14
    0.8%
    320
    +0.12
    0.7%
    323
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.14
    0.02
    192
    +0.12
    0.02
    116
    +0.11
    0.02
    Negative Logits
     margins
    -1.52
    rait
    -1.51
    oge
    -1.50
     %)
    -1.48
    tone
    -1.43
    enes
    -1.43
    core
    -1.42
    inks
    -1.42
    ourier
    -1.41
    UIT
    -1.40
    POSITIVE LOGITS
     Springer
    1.47
     Gö
    1.45
     lic
    1.42
    ãĢĢãĢĢ
    1.37
     AUTH
    1.34
    čč
    1.29
     Lithuan
    1.26
     issuance
    1.26
     certificate
    1.24
     Defendant
    1.24
    Activations Density 0.091%

    No Known Activations