© 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. 13974
    Prev
    Next
    INDEX
    Explanations

    administrative tasks and configurations related to user permissions

    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
    17
    +0.19
    1.1%
    369
    +0.13
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.19
    0.02
    67
    +0.13
    0.04
    482
    +0.13
    0.06
    Negative Logits
    )\]
    -2.78
    )\].
    -2.28
     respectively
    -2.28
    )),
    -2.08
    )],
    -2.00
    '));
    -1.83
    ))
    -1.82
    '))
    -1.81
    )];
    -1.78
    ()))
    -1.77
    POSITIVE LOGITS
    ¾
    2.05
    Īĺ
    2.00
    Ģ
    2.00
    ¢
    1.95
    ¶
    1.79
    ½
    1.77
    ľĵ
    1.72
    ĩ
    1.69
    ĭ
    1.66
    ı
    1.65
    Activations Density 1.059%

    No Known Activations