© 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. 27673
    Prev
    Next
    INDEX
    Explanations

    terms related to elastic materials and their properties

    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%
    2
    +0.13
    0.7%
    274
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.14
    0.02
    484
    +0.13
    0.02
    82
    +0.11
    0.01
    Negative Logits
     turn
    -1.56
     logical
    -1.52
     stars
    -1.49
     pans
    -1.48
     Month
    -1.41
     ever
    -1.40
     pupils
    -1.37
     investigated
    -1.36
    wards
    -1.35
     Publ
    -1.33
    POSITIVE LOGITS
    ¥
    2.71
    ĻĤ
    2.52
    ģ
    2.52
    ķ
    2.42
    Ī
    2.37
    ¢
    2.35
    Ĵ
    2.35
    ¬
    2.31
    §
    2.30
    ¡
    2.28
    Activations Density 0.080%

    No Known Activations