© 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. 26237
    Prev
    Next
    INDEX
    Explanations

    references to polymers and polymer research

    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
    271
    +0.17
    0.9%
    111
    +0.14
    0.8%
    313
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.05
    271
    +0.14
    0.01
    379
    +0.11
    0.03
    Negative Logits
     '''
    -1.47
     ![](
    -1.43
     weights
    -1.42
     Edwards
    -1.41
     supposed
    -1.40
     cursor
    -1.36
     bilateral
    -1.36
     ``
    -1.35
     Virgin
    -1.35
     Spacewatch
    -1.34
    POSITIVE LOGITS
    »
    1.86
    Ŀ
    1.86
    ¼
    1.84
    »¿
    1.81
    Ļ
    1.79
    cif
    1.78
    ½
    1.78
    ĥ
    1.74
    ģ
    1.73
    IJ
    1.69
    Activations Density 0.159%

    No Known Activations