© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 12074
    Prev
    Next
    INDEX
    Explanations

    references to telemedicine and telepresence in the context of disaster response

    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
    505
    +0.12
    0.7%
    420
    +0.12
    0.7%
    329
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.12
    0.02
    98
    +0.12
    0.00
    420
    +0.10
    0.02
    Negative Logits
     uniforms
    -1.83
    ¿½
    -1.82
    Ļª
    -1.74
    Ĺ
    -1.74
    Ł
    -1.71
     conductor
    -1.71
    lectric
    -1.66
     Chevrolet
    -1.65
     electric
    -1.64
    §
    -1.64
    POSITIVE LOGITS
     PubMed
    4.05
     Cochrane
    3.31
     databases
    2.92
     journals
    2.81
     reviews
    2.59
     bibli
    2.58
     reviewers
    2.57
    Pub
    2.54
     Reviews
    2.43
     published
    2.43
    Activations Density 0.289%

    No Known Activations