© 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. 13499
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly those related to application context and entity management

    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
    +0.23
    1.3%
    156
    +0.14
    0.8%
    397
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.23
    0.01
    397
    +0.14
    0.10
    17
    +0.14
    0.09
    Negative Logits
     summation
    -1.74
     reversal
    -1.71
     penalty
    -1.68
     margin
    -1.66
     counted
    -1.59
     regards
    -1.57
     inequality
    -1.48
     bills
    -1.46
    Decided
    -1.45
     proportions
    -1.45
    POSITIVE LOGITS
    ª
    6.03
    ĨĴ
    5.99
    ¢
    5.84
    Ļª
    5.80
    ¿
    5.68
    ±
    5.67
    <|outofrange|>
    5.60
    ↵↵
    5.60
    <|outofrange|>
    5.60
            ↵
    5.60
    Activations Density 1.464%

    No Known Activations