© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12030
    Prev
    Next
    INDEX
    Explanations

    programming-related functions or methods related to data manipulation and file processing

    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
    +0.18
    1.1%
    466
    +0.17
    1.0%
    257
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.18
    0.01
    260
    +0.17
    0.10
    36
    +0.11
    0.10
    Negative Logits
    don
    -1.52
    edin
    -1.46
    story
    -1.42
    eous
    -1.37
     fever
    -1.36
     Notice
    -1.33
     Suite
    -1.32
     centralized
    -1.30
    quart
    -1.29
    hot
    -1.29
    POSITIVE LOGITS
    Ļª
    4.16
    ª
    4.03
    °
    3.85
    Ĵ
    3.82
    İ
    3.78
    <|outofrange|>
    3.72
    <|outofrange|>
    3.72
    ↵
    3.72
    ↵↵
    3.72
     ↵
    3.72
    Activations Density 0.926%

    No Known Activations