© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 12299
    Prev
    Next
    INDEX
    Explanations

    words associated with elasticity and plasticity, specifically in scientific 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.17
    1.0%
    156
    +0.11
    0.6%
    408
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.17
    0.04
    1
    +0.11
    0.02
    98
    +0.10
    0.01
    Negative Logits
    lessness
    -2.09
    lessly
    -2.06
    ments
    -1.81
    riers
    -1.76
    bed
    -1.72
    illard
    -1.68
    bered
    -1.64
    ries
    -1.61
    ings
    -1.57
    bage
    -1.57
    POSITIVE LOGITS
     acid
    2.07
    ity
    2.01
     Acid
    1.92
    ¨
    1.70
    fusion
    1.69
    «
    1.56
     Surgery
    1.53
    Ħ
    1.53
    ¡
    1.51
    ArgumentException
    1.51
    Activations Density 0.335%

    No Known Activations