© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 24215
    Prev
    Next
    INDEX
    Explanations

    terms related to cricket and its terminology

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    410
    +0.15
    0.8%
    211
    +0.13
    0.7%
    111
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.02
    37
    +0.13
    0.01
    77
    +0.12
    0.01
    Negative Logits
    ĸ´
    -2.08
    ¯
    -1.83
    į
    -1.82
    Ļª
    -1.72
    Ħ
    -1.68
    ·¸
    -1.67
    µ
    -1.61
     Virgin
    -1.60
     knowledge
    -1.59
    Ł
    -1.55
    POSITIVE LOGITS
    ets
    2.16
    ettes
    2.14
    bour
    1.90
    neys
    1.77
    series
    1.64
    igan
    1.62
     (,
    1.61
    seys
    1.60
    nuts
    1.56
    lee
    1.56
    Activations Density 0.122%

    No Known Activations