© 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. 4-RES-SM
    11. 9667
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming and data structures

    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
    156
    +0.28
    1.8%
    307
    +0.23
    1.5%
    21
    +0.19
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.28
    0.14
    492
    +0.23
    0.13
    108
    +0.19
    0.20
    Negative Logits
    ģ
    -1.85
    lement
    -1.60
    liness
    -1.58
    »¿
    -1.52
    apter
    -1.51
    İ
    -1.45
    Ĭ
    -1.44
    Ŀ
    -1.44
    corn
    -1.42
    ī
    -1.39
    POSITIVE LOGITS
    npmjs
    1.49
     ageing
    1.32
     parl
    1.31
    NAT
    1.30
     rehabilitation
    1.25
     tumour
    1.24
     native
    1.21
     anaest
    1.19
     intensive
    1.19
     palliative
    1.19
    Activations Density 5.588%

    No Known Activations