© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30158
    Prev
    Next
    INDEX
    Explanations

    references to various licenses and licensing terms

    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
    2
    +0.17
    1.0%
    217
    +0.13
    0.8%
    42
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.17
    0.02
    2
    +0.13
    0.03
    329
    +0.13
    0.02
    Negative Logits
    ĨĴ
    -2.35
    ĵ
    -1.81
     grief
    -1.80
    Ł
    -1.79
    itan
    -1.72
    ĥ½
    -1.67
     hers
    -1.66
    ¯
    -1.60
    _**
    -1.58
     mour
    -1.58
    POSITIVE LOGITS
     Agreement
    2.15
     agreement
    2.12
     HOLDERS
    1.93
     expires
    1.87
     agreements
    1.83
     waiver
    1.80
     revocation
    1.77
     privileges
    1.71
    fficients
    1.70
    ivation
    1.69
    Activations Density 0.129%

    No Known Activations