© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25910
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions or health issues

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.34
    2.0%
    136
    +0.22
    1.3%
    271
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.34
    0.19
    111
    +0.22
    0.25
    5
    +0.17
    0.23
    Negative Logits
     Palin
    -1.33
    ↵
    -1.32
    \]](
    -1.27
     boost
    -1.26
     Boost
    -1.26
    UPDATE
    -1.22
     Barr
    -1.21
    quito
    -1.21
     Comic
    -1.21
    FW
    -1.20
    POSITIVE LOGITS
    Ļ
    2.23
    Īĺ
    1.67
    ¿
    1.65
    Ĥ
    1.59
    ¯
    1.56
     respectively
    1.55
    aced
    1.53
    ½
    1.51
    ¾
    1.45
    ¤
    1.44
    Activations Density 2.106%

    No Known Activations