© 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. 25946
    Prev
    Next
    INDEX
    Explanations

    terms related to heart conditions and anatomical structures

    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
    +0.14
    0.8%
    71
    +0.13
    0.8%
    45
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.03
    271
    +0.13
    0.01
    156
    +0.13
    0.01
    Negative Logits
    ating
    -1.52
     civilized
    -1.51
    nered
    -1.50
    eds
    -1.48
     believing
    -1.48
     else
    -1.47
    ered
    -1.47
     Said
    -1.45
     respectful
    -1.45
    >(
    -1.40
    POSITIVE LOGITS
    £
    2.84
    ¥
    2.33
    ¤
    2.22
    ļ
    2.09
    ¨
    2.01
    ŀ
    2.00
    µ
    1.97
    ī
    1.92
    ²
    1.92
    °
    1.91
    Activations Density 0.040%

    No Known Activations