© 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. 29203
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate work or ongoing projects

    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
    470
    +0.12
    0.7%
    330
    +0.11
    0.6%
    89
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.05
    282
    +0.11
    0.04
    190
    +0.10
    0.04
    Negative Logits
    ¼
    -2.41
    Ļª
    -2.30
    İ
    -1.87
    ī
    -1.86
    »
    -1.86
    ı
    -1.80
    -1.78
    <|outofrange|>
    -1.78
    ↵↵↵
    -1.78
    č↵
    -1.78
    POSITIVE LOGITS
    oly
    1.64
     crafts
    1.53
    adata
    1.43
    uster
    1.40
    json
    1.39
    ore
    1.39
    aded
    1.39
    eclipse
    1.36
     Publ
    1.35
    odot
    1.35
    Activations Density 0.499%

    No Known Activations