© 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. 1-RES-SM
    11. 29291
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and bounds

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    376
    +0.13
    0.8%
    478
    +0.13
    0.7%
    408
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.13
    0.03
    455
    +0.13
    0.02
    284
    +0.12
    0.03
    Negative Logits
    ember
    -1.99
    ILE
    -1.69
    ename
    -1.62
    aten
    -1.61
    OST
    -1.60
    kan
    -1.60
     sense
    -1.54
    clamation
    -1.53
    idin
    -1.50
    adin
    -1.49
    POSITIVE LOGITS
    ı
    2.62
    ĥ
    2.57
    ľ
    2.50
    ļ
    2.44
    ī
    2.36
    ĥ½
    2.33
    Īĺ
    2.25
    «
    2.24
    ↵
    2.20
    2.20
    Activations Density 0.129%

    No Known Activations