© 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. 9734
    Prev
    Next
    INDEX
    Explanations

    queries related to troubleshooting and problem-solving with technology

    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
    416
    +0.13
    0.7%
    81
    +0.12
    0.7%
    384
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.13
    0.08
    81
    +0.12
    0.07
    465
    +0.12
    0.10
    Negative Logits
    ^\[[@
    -1.92
    ]{.
    -1.75
    .^[@
    -1.66
    ^),
    -1.52
    ^](#
    -1.51
    )\]
    -1.48
    ^**
    -1.48
    ^)
    -1.46
    imon
    -1.41
    ^âĪĴ
    -1.40
    POSITIVE LOGITS
    ($_
    1.72
     strlen
    1.70
    odb
    1.68
     workaround
    1.67
    stdio
    1.53
    convert
    1.52
     findViewById
    1.52
    stringify
    1.48
     localhost
    1.48
    ibernate
    1.47
    Activations Density 1.029%

    No Known Activations