© 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. 4-RES-SM
    11. 13050
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronic devices, particularly in the context of semiconductors and their components

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.16
    0.9%
    78
    +0.14
    0.8%
    436
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.16
    0.04
    436
    +0.14
    0.03
    382
    +0.13
    0.02
    Negative Logits
    inctions
    -2.30
    orms
    -2.10
    places
    -2.05
    ships
    -1.96
    redients
    -1.95
    hots
    -1.93
     pains
    -1.92
     sexes
    -1.91
    asms
    -1.91
     flavors
    -1.89
    POSITIVE LOGITS
    ↵
    6.02
    6.02
    ↵↵
    6.02
    <|outofrange|>
    6.02
    ↵  âĢĥ
    6.02
         ↵
    6.02
    <|outofrange|>
    6.02
    <|outofrange|>
    6.02
    <|outofrange|>
    6.02
    <|outofrange|>
    6.02
    Activations Density 0.317%

    No Known Activations