© 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. 2-RES-SM
    11. 27418
    Prev
    Next
    INDEX
    Explanations

    phrases referring to roles, functionalities, or responsibilities in various contexts

    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
    186
    +0.17
    1.0%
    320
    +0.16
    0.9%
    331
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.17
    0.10
    178
    +0.16
    0.10
    186
    +0.15
    0.05
    Negative Logits
     options
    -1.95
     perspectives
    -1.68
     reasons
    -1.63
    mmas
    -1.59
    ħ
    -1.56
     notes
    -1.55
    cember
    -1.54
    ·¸
    -1.53
     clues
    -1.52
     possibilities
    -1.51
    POSITIVE LOGITS
    unes
    1.57
    ently
    1.41
     remotely
    1.41
     %.
    1.39
    %.
    1.36
     reproduce
    1.35
    .]{}
    1.35
    wordpress
    1.34
    atically
    1.34
     %>
    1.33
    Activations Density 2.416%

    No Known Activations