© 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. 26445
    Prev
    Next
    INDEX
    Explanations

    references to decision-making processes and related terms

    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
    466
    +0.13
    0.7%
    189
    +0.13
    0.7%
    313
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.13
    0.04
    351
    +0.13
    0.04
    66
    +0.11
    0.04
    Negative Logits
    ¿½
    -2.68
    ·¸
    -2.40
    <|outofrange|>
    -2.29
    ↵↵
    -2.29
    ↵
    -2.29
    -2.29
    <|outofrange|>
    -2.29
    ↵
    -2.29
    <|outofrange|>
    -2.29
    č↵
    -2.29
    POSITIVE LOGITS
     polls
    1.89
    ulator
    1.72
    rieved
    1.70
    ontal
    1.65
    otrop
    1.63
    atum
    1.61
    erior
    1.59
    etable
    1.57
    ata
    1.55
    clin
    1.54
    Activations Density 0.776%

    No Known Activations