© 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. 24650
    Prev
    Next
    INDEX
    Explanations

    references to U.S. government and military activities

    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
    271
    +0.22
    1.2%
    23
    +0.17
    1.0%
    111
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.22
    0.18
    271
    +0.17
    0.07
    17
    +0.14
    0.08
    Negative Logits
    º
    -3.10
    ĥ½
    -3.04
    ¾
    -2.99
    µ
    -2.95
    ↵
    -2.92
    ↵
    -2.92
    -2.92
    -2.92
    <|outofrange|>
    -2.92
    -2.92
    POSITIVE LOGITS
    ]>
    1.79
     nowhere
    1.61
    also
    1.48
    URAL
    1.43
    estly
    1.37
    inous
    1.36
    ough
    1.32
    ãģĵ
    1.32
     next
    1.32
     pleaded
    1.31
    Activations Density 0.939%

    No Known Activations