© 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. 2-RES-SM
    11. 28419
    Prev
    Next
    INDEX
    Explanations

    information related to transportation services and ticket pricing

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.15
    0.8%
    7
    +0.14
    0.8%
    210
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.15
    0.05
    251
    +0.14
    0.04
    248
    +0.12
    0.07
    Negative Logits
    mathrsfs
    -2.07
    TEGER
    -1.90
    raints
    -1.75
    Boolean
    -1.67
    олÑĮз
    -1.64
     tumor
    -1.56
     wrong
    -1.53
    æģ¯
    -1.51
    efficacy
    -1.50
    ArgumentException
    -1.48
    POSITIVE LOGITS
     railway
    1.94
     north
    1.83
     kilomet
    1.81
     petrol
    1.81
     inland
    1.75
     tours
    1.71
     east
    1.70
     metres
    1.70
     south
    1.66
     Rail
    1.65
    Activations Density 1.707%

    No Known Activations