© 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. 13956
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix 'ator', indicating roles or functions of operators, particularly in technological or engineering 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
    187
    +0.13
    0.8%
    73
    +0.12
    0.7%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.13
    0.01
    73
    +0.12
    0.03
    399
    +0.12
    0.02
    Negative Logits
    ĻĤ
    -2.26
    ĥ½
    -2.17
    ĺ
    -2.10
    ª
    -1.94
    Ĭ
    -1.91
    ¿½
    -1.91
    Ļª
    -1.88
    Īĺ
    -1.86
    ©
    -1.84
    ¸
    -1.84
    POSITIVE LOGITS
    ially
    2.37
    ial
    1.95
    ius
    1.87
    ials
    1.79
    ium
    1.75
    ics
    1.68
    aching
    1.67
    ism
    1.65
     estoppel
    1.53
    ically
    1.52
    Activations Density 0.243%

    No Known Activations