© 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. 12078
    Prev
    Next
    INDEX
    Explanations

    specific technical terminology related to thermoelectric materials and devices

    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
    417
    +0.14
    0.8%
    309
    +0.13
    0.7%
    47
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.14
    0.07
    154
    +0.13
    0.07
    469
    +0.12
    0.07
    Negative Logits
    pancy
    -1.87
     chance
    -1.78
    ateness
    -1.73
    cknowled
    -1.70
    ophyll
    -1.65
     sentence
    -1.63
     genotype
    -1.59
    ymoon
    -1.58
    олÑĮко
    -1.58
    ophagus
    -1.57
    POSITIVE LOGITS
     devices
    3.75
     systems
    3.47
     apparatuses
    3.27
     machines
    3.19
     technologies
    3.08
     assemblies
    2.95
     designs
    2.83
     schemes
    2.80
    İ
    2.77
     Devices
    2.72
    Activations Density 0.758%

    No Known Activations