© 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. 24586
    Prev
    Next
    INDEX
    Explanations

    references to people or collective groups

    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
    +0.27
    1.6%
    376
    +0.16
    0.9%
    365
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.27
    0.03
    365
    +0.16
    0.03
    434
    +0.15
    0.02
    Negative Logits
    ĥ½
    -2.60
    Ļª
    -2.16
    -2.14
    -2.14
    ↵
    -2.14
    ↵  âĢĥ
    -2.14
    <|outofrange|>
    -2.14
    ·
    -2.14
    ↵
    -2.14
    ↵
    -2.14
    POSITIVE LOGITS
    ega
    1.68
    arat
    1.64
    adder
    1.56
    got
    1.44
    add
    1.43
    olini
    1.38
    push
    1.37
    if
    1.37
    enzie
    1.36
    plist
    1.35
    Activations Density 0.308%

    No Known Activations