© 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. 27631
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or actions

    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
    129
    +0.15
    0.8%
    173
    +0.14
    0.8%
    410
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.15
    0.02
    129
    +0.14
    0.01
    103
    +0.13
    0.02
    Negative Logits
    ĥ½
    -2.30
    ¸
    -2.23
    ·
    -2.23
    Ļª
    -2.23
    ij
    -2.22
    ĨĴ
    -2.18
    £
    -2.15
    ĻĤ
    -2.13
    Ĥ¬
    -2.07
     ↵
    -2.06
    POSITIVE LOGITS
     note
    1.79
     notice
    1.73
    cox
    1.65
     open
    1.64
    gery
    1.56
    quez
    1.55
     put
    1.53
     bail
    1.49
     insert
    1.49
    give
    1.49
    Activations Density 0.045%

    No Known Activations