© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11694
    Prev
    Next
    INDEX
    Explanations

    terms related to radio frequency and communication technology

    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
    292
    +0.13
    0.7%
    129
    +0.12
    0.6%
    443
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.13
    0.02
    292
    +0.12
    0.02
    289
    +0.11
    0.01
    Negative Logits
    IJ
    -2.35
    §
    -2.05
    ¿
    -2.02
    ĸ
    -1.94
    ĸ´
    -1.92
     recommend
    -1.83
    Ŀ
    -1.83
    ľĵ
    -1.82
    ĭ
    -1.82
    ĵ
    -1.80
    POSITIVE LOGITS
    frequency
    2.85
    isot
    2.78
    actively
    2.42
    immun
    2.28
    activity
    2.16
     Broadcasting
    2.15
    active
    2.13
    head
    2.07
     stations
    1.99
     Frequency
    1.98
    Activations Density 0.102%

    No Known Activations