© 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. 13899
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and terminology

    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
    233
    +0.14
    0.8%
    382
    +0.14
    0.8%
    193
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.14
    0.18
    178
    +0.14
    0.15
    219
    +0.12
    0.12
    Negative Logits
    ·¸
    -2.06
    ¾
    -1.96
    Īĺ
    -1.91
    ³
    -1.80
    «
    -1.78
    Ĥ¬
    -1.71
    ĸ´
    -1.70
    ²
    -1.69
    ª
    -1.66
    Ń
    -1.65
    POSITIVE LOGITS
    [^
    2.08
    )|\
    1.68
    );\
    1.61
    **\
    1.52
    onuclear
    1.42
    **.
    1.40
    [@
    1.39
     microbiota
    1.33
    )|
    1.32
    `.
    1.30
    Activations Density 7.165%

    No Known Activations