© 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. 4-RES-SM
    11. 9756
    Prev
    Next
    INDEX
    Explanations

    information about birth and death dates of individuals

    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
    +0.15
    0.8%
    21
    +0.13
    0.7%
    375
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.15
    0.01
    422
    +0.13
    0.01
    266
    +0.13
    0.01
    Negative Logits
    ¢
    -2.28
    ¶
    -2.18
    ģ
    -2.10
    ¬
    -2.06
    ¿½
    -1.97
    º
    -1.86
    ķ
    -1.83
    Ĺ
    -1.79
    Ĥ¬
    -1.78
    Ĥ
    -1.77
    POSITIVE LOGITS
     ):
    1.89
    ):
    1.83
     April
    1.80
    )',
    1.73
     ),
    1.71
     March
    1.70
     February
    1.66
    ,)
    1.66
     December
    1.65
     November
    1.65
    Activations Density 0.016%

    No Known Activations