© 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. 12618
    Prev
    Next
    INDEX
    Explanations

    specific numerical patterns and identifiers related to data formats

    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
    12
    +0.21
    1.2%
    186
    +0.17
    1.0%
    153
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.21
    0.16
    153
    +0.17
    0.07
    353
    +0.16
    0.06
    Negative Logits
    etine
    -1.74
    ferencing
    -1.54
    linked
    -1.45
     etc
    -1.44
    ging
    -1.40
    ferentially
    -1.33
     across
    -1.31
    uously
    -1.31
    coding
    -1.31
    rolled
    -1.30
    POSITIVE LOGITS
    ĨĴ
    4.16
    ±
    3.92
    ĻĤ
    3.92
    ©
    3.85
    ¤
    3.81
    3.77
    <|outofrange|>
    3.77
    ↵
    3.77
    č↵
    3.77
    3.77
    Activations Density 5.318%

    No Known Activations