© 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. 24609
    Prev
    Next
    INDEX
    Explanations

    mentions of California

    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
    156
    +0.19
    1.1%
    182
    +0.16
    0.9%
    71
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.19
    0.03
    71
    +0.16
    0.04
    439
    +0.14
    0.02
    Negative Logits
    ĥ½
    -3.01
    ĺ
    -2.99
    ¹
    -2.90
    Ķ
    -2.84
    ´
    -2.77
    Ħ
    -2.72
    ↵  ↵
    -2.71
    ↵
    -2.71
    -2.71
    -2.71
    POSITIVE LOGITS
    ÃŃa
    1.75
    itrile
    1.72
    imiento
    1.64
    mont
    1.57
    illac
    1.56
     Springs
    1.54
    izumab
    1.52
    ivable
    1.51
    ville
    1.48
    Tech
    1.48
    Activations Density 0.088%

    No Known Activations