© 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. 2-RES-SM
    11. 31596
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions related to programming or data analysis

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    12
    +0.16
    0.9%
    400
    +0.16
    0.9%
    72
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.16
    0.11
    72
    +0.16
    0.07
    398
    +0.14
    0.11
    Negative Logits
    IJ
    -2.41
    »¿
    -2.38
    Ļª
    -2.18
    Ĩ
    -2.12
    ŀ
    -2.12
    ī
    -2.11
    ĻĤ
    -2.09
    ·
    -2.06
    °
    -2.06
    Ĵ
    -2.05
    POSITIVE LOGITS
    eps
    1.62
    edia
    1.56
    akes
    1.40
    akia
    1.35
     EDTA
    1.34
    `,
    1.32
    .*]{},
    1.32
    ushes
    1.32
    oulder
    1.31
    ipes
    1.29
    Activations Density 3.435%

    No Known Activations