© 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. 1-RES-SM
    11. 28548
    Prev
    Next
    INDEX
    Explanations

    biological processes and their regulatory mechanisms

    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
    +0.22
    1.3%
    271
    +0.21
    1.2%
    47
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.22
    0.05
    47
    +0.21
    0.07
    7
    +0.18
    0.04
    Negative Logits
    optera
    -1.56
     tomorrow
    -1.53
    orect
    -1.42
     needs
    -1.41
    estry
    -1.39
    aby
    -1.37
    osp
    -1.36
     GP
    -1.35
    hp
    -1.34
     minded
    -1.34
    POSITIVE LOGITS
    ı
    3.03
    ĺ
    2.64
    Ļ
    2.53
    ĻĤ
    2.49
    Īĺ
    2.42
    ¦
    2.42
    Ĩ
    2.41
    »¿
    2.41
    ¤
    2.41
    ¥
    2.41
    Activations Density 0.716%

    No Known Activations