© 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. 30700
    Prev
    Next
    INDEX
    Explanations

    references to patents and patent-related topics

    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
    507
    +0.15
    0.9%
    425
    +0.14
    0.8%
    104
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.15
    0.02
    177
    +0.14
    0.01
    425
    +0.13
    0.01
    Negative Logits
    ĥ½
    -2.29
    ĨĴ
    -2.00
              ↵
    -1.98
     ↵
    -1.98
    -1.98
    ↵
    -1.98
     ↵
    -1.98
    -1.98
    -1.98
    ↵
    -1.98
    POSITIVE LOGITS
    icul
    1.82
    enance
    1.68
    iors
    1.61
    nals
    1.58
    rization
    1.54
    stood
    1.51
    tah
    1.47
    riz
    1.46
    ocols
    1.45
    isan
    1.42
    Activations Density 0.047%

    No Known Activations