© 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. 24216
    Prev
    Next
    INDEX
    Explanations

    references to various types of environments

    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
    +0.16
    1.0%
    219
    +0.13
    0.8%
    458
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.16
    0.03
    450
    +0.13
    0.02
    141
    +0.10
    0.01
    Negative Logits
    ŀ
    -3.43
    -3.34
     ↵
    -3.34
    -3.34
    ↵
    -3.34
    č↵
    -3.34
    ↵
    -3.34
    ↵
    -3.34
    <|outofrange|>
    -3.34
    ↵
    -3.34
    POSITIVE LOGITS
     variables
    1.79
     scenarios
    1.59
     scenario
    1.59
    "}](#
    1.55
    Variables
    1.54
    floor
    1.52
    ically
    1.52
    ETHOD
    1.50
    DM
    1.50
     module
    1.48
    Activations Density 0.102%

    No Known Activations