© 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. 29712
    Prev
    Next
    INDEX
    Explanations

    specific years mentioned in the text

    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
    430
    +0.12
    0.7%
    320
    +0.10
    0.6%
    111
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.12
    0.02
    273
    +0.10
    0.01
    288
    +0.10
    0.02
    Negative Logits
    ı
    -2.94
    ij
    -2.89
    Ħ
    -2.84
    ®
    -2.72
    ĺ
    -2.67
    ĵ
    -2.62
    Ļ
    -2.62
    Ł
    -2.59
    ĥ
    -2.56
    ¿½
    -2.55
    POSITIVE LOGITS
    atisf
    1.74
    ervice
    1.72
    proving
    1.68
    ponse
    1.68
    pletion
    1.68
    ancell
    1.61
    cery
    1.51
    plement
    1.47
    amily
    1.45
    uez
    1.43
    Activations Density 0.058%

    No Known Activations