© 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. 2-RES-SM
    11. 12365
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    +0.27
    1.6%
    369
    +0.22
    1.3%
    410
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.27
    0.06
    410
    +0.22
    0.12
    350
    +0.16
    0.07
    Negative Logits
    "}](#
    -2.03
    ikov
    -1.83
    zyk
    -1.53
    ginx
    -1.39
    icz
    -1.35
    )](#
    -1.35
    yz
    -1.35
    ystems
    -1.34
    inary
    -1.32
    =/
    -1.29
    POSITIVE LOGITS
    ³
    1.98
    Ľ
    1.81
    Ĩ
    1.77
    Į
    1.72
    Ĭ
    1.57
    Ķ
    1.57
    ¬
    1.54
     importantly
    1.54
     Comments
    1.53
    ¿½
    1.48
    Activations Density 1.569%

    No Known Activations