© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 9324
    Prev
    Next
    INDEX
    Explanations

    technical terms and file types related to programming or computer science

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.26
    1.5%
    307
    +0.25
    1.5%
    348
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.26
    0.02
    181
    +0.25
    0.11
    143
    +0.18
    0.02
    Negative Logits
     METHODS
    -1.51
     Thy
    -1.49
     Conditions
    -1.47
     Disorder
    -1.46
     oneself
    -1.45
     Infl
    -1.43
     circumference
    -1.40
     uniformity
    -1.40
     according
    -1.38
     annual
    -1.36
    POSITIVE LOGITS
    Ļª
    5.13
    ¾
    4.93
    º
    4.92
    ª
    4.76
    ®
    4.63
    Ń
    4.58
    «
    4.58
    ĨĴ
    4.55
    Ĵ
    4.45
    ŀ
    4.40
    Activations Density 1.063%

    No Known Activations