© 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. 2-RES-SM
    11. 10750
    Prev
    Next
    INDEX
    Explanations

    conditions and disclaimers related to legal or contractual obligations

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.17
    1.0%
    369
    +0.13
    0.8%
    139
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.17
    0.01
    18
    +0.13
    0.01
    139
    +0.12
    0.02
    Negative Logits
    alls
    -1.78
    ayout
    -1.59
    hm
    -1.58
    ancial
    -1.56
    alities
    -1.49
    áĢ¯
    -1.48
    ursed
    -1.46
    àµį
    -1.45
    icity
    -1.45
    ity
    -1.44
    POSITIVE LOGITS
    ¼
    2.87
    ¸
    2.40
    IJ
    2.36
    į
    2.34
    ½
    2.32
    ¹
    2.29
    ĨĴ
    2.25
    ĸ´
    2.23
    Ĺ
    2.21
    ®
    2.19
    Activations Density 0.065%

    No Known Activations