© 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 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. 9836
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize quantity or amounts

    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
    161
    +0.15
    0.8%
    98
    +0.15
    0.8%
    70
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.15
    0.05
    457
    +0.15
    0.04
    328
    +0.13
    0.04
    Negative Logits
    kok
    -1.70
     goodbye
    -1.60
    "}](#
    -1.56
    ://
    -1.51
    agi
    -1.43
     0000000000000000000000000000000000
    -1.43
    rov
    -1.40
    ruptcy
    -1.40
    ksen
    -1.39
    ãĥ¥
    -1.39
    POSITIVE LOGITS
     resources
    1.72
    Ľ
    1.61
    .),
    1.58
     possessions
    1.58
    »¿
    1.55
     usable
    1.52
     available
    1.50
    '),
    1.49
    ials
    1.45
    )."
    1.42
    Activations Density 0.340%

    No Known Activations