© 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 EvalsExportsAPI 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. 26059
    Prev
    Next
    INDEX
    Explanations

    references to numerical rankings or positions

    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
    87
    +0.12
    0.7%
    497
    +0.12
    0.7%
    458
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.12
    0.03
    497
    +0.12
    0.03
    87
    +0.11
    0.03
    Negative Logits
     respectively
    -1.60
    ilot
    -1.59
    ational
    -1.58
    rent
    -1.51
    ARRANT
    -1.51
    istor
    -1.51
    abilities
    -1.50
     Reserve
    -1.50
    anson
    -1.49
     */
    -1.47
    POSITIVE LOGITS
    meal
    1.71
    wine
    1.64
    define
    1.60
    kubuntu
    1.54
     parte
    1.51
    !/
    1.51
    Ubuntu
    1.50
    ¼
    1.42
    align
    1.40
    include
    1.40
    Activations Density 0.101%

    No Known Activations