© 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. 14973
    Prev
    Next
    INDEX
    Explanations

    terms related to processes of creation and development in various 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
    78
    +0.17
    1.0%
    348
    +0.14
    0.8%
    9
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    215
    +0.17
    0.07
    265
    +0.14
    0.02
    287
    +0.11
    0.06
    Negative Logits
    (@"
    -1.49
    npmjs
    -1.43
    arthy
    -1.29
    wrote
    -1.28
     typeof
    -1.28
    mozilla
    -1.27
    sembles
    -1.24
    Simplify
    -1.23
    cludes
    -1.22
    newcommand
    -1.19
    POSITIVE LOGITS
     of
    2.50
     thereof
    2.34
     process
    2.33
     stage
    1.86
     phase
    1.75
    ANCE
    1.75
     requirement
    1.72
     stages
    1.64
     rate
    1.63
     OF
    1.61
    Activations Density 0.525%

    No Known Activations