© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11039
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structures

    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
    293
    +0.17
    1.0%
    320
    +0.16
    0.9%
    76
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.17
    0.12
    342
    +0.16
    0.06
    220
    +0.16
    0.06
    Negative Logits
    ()).
    -1.46
    ilt
    -1.37
    ();
    -1.35
     poor
    -1.35
    uest
    -1.34
    ()</
    -1.34
     record
    -1.34
    fulness
    -1.33
     dispute
    -1.30
    oop
    -1.28
    POSITIVE LOGITS
    chet
    1.79
    phalt
    1.54
     huh
    1.48
    igt
    1.46
    cco
    1.35
    isia
    1.33
    cket
    1.31
    apers
    1.30
     hug
    1.30
    orters
    1.30
    Activations Density 5.130%

    No Known Activations