© 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. 13149
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial activity and manufacturing processes

    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
    156
    +0.17
    0.9%
    393
    +0.14
    0.8%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.17
    0.02
    451
    +0.14
    0.01
    29
    +0.11
    0.01
    Negative Logits
     hers
    -1.91
    ureus
    -1.63
    arma
    -1.57
    qq
    -1.52
     unpublished
    -1.48
    CDATA
    -1.46
    ÑĢав
    -1.44
     lazy
    -1.43
    unctive
    -1.42
     parental
    -1.42
    POSITIVE LOGITS
    µ
    2.78
    ¼
    2.64
    £
    2.62
    ·
    2.60
    ½
    2.51
    ¡
    2.51
    »¿
    2.51
    ´
    2.44
    ®
    2.40
    ·¸
    2.40
    Activations Density 0.101%

    No Known Activations