© 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 EvalsExportsAPI 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. 12991
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming languages and their interactions

    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
    189
    +0.14
    0.8%
    307
    +0.12
    0.7%
    75
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.14
    0.06
    401
    +0.12
    0.03
    146
    +0.11
    0.06
    Negative Logits
    ĵ
    -4.53
    ↵
    -4.34
    <|outofrange|>
    -4.34
    ↵
    -4.34
    <|outofrange|>
    -4.34
    -4.34
       ↵
    -4.34
    -4.34
    ↵
    -4.34
    -4.34
    POSITIVE LOGITS
     context
    2.10
    cript
    1.99
    js
    1.85
     realm
    1.82
     Settings
    1.79
    rb
    1.79
    scala
    1.78
    cpp
    1.75
    context
    1.74
     mode
    1.72
    Activations Density 0.437%

    No Known Activations