© 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. 28857
    Prev
    Next
    INDEX
    Explanations

    references to global issues or phenomena

    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
    156
    +0.20
    1.1%
    29
    +0.14
    0.8%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.20
    0.02
    429
    +0.14
    0.02
    266
    +0.11
    0.02
    Negative Logits
    ository
    -1.91
    rir
    -1.70
     arbitrary
    -1.59
     sacrifice
    -1.58
    fficient
    -1.53
    lla
    -1.52
     died
    -1.50
    apest
    -1.49
    heets
    -1.48
    lessly
    -1.48
    POSITIVE LOGITS
    ķ
    2.49
    Ĺ
    2.31
    Ł
    2.25
    ĵ
    2.17
    ĺ
    2.15
    Ħ
    2.13
    £
    2.03
    °
    2.03
    µ
    1.94
    isation
    1.93
    Activations Density 0.067%

    No Known Activations