© 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. 24694
    Prev
    Next
    INDEX
    Explanations

    references to scientific papers or studies

    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
    108
    +0.14
    0.8%
    408
    +0.13
    0.7%
    40
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.14
    0.02
    40
    +0.13
    0.02
    408
    +0.12
    0.01
    Negative Logits
    Ĺ
    -2.75
    ī
    -2.67
    ¹
    -2.60
    °
    -2.54
    Īĺ
    -2.53
    ±
    -2.50
    ij
    -2.32
    Ģ
    -2.32
    ħ
    -2.25
    ĵ
    -2.25
    POSITIVE LOGITS
    ström
    1.82
    orsche
    1.80
    sson
    1.71
    uthan
    1.68
    ainen
    1.67
    artments
    1.59
    izumab
    1.59
    emann
    1.59
    ipzig
    1.58
    ÄŁ
    1.57
    Activations Density 0.095%

    No Known Activations