© 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. 28866
    Prev
    Next
    INDEX
    Explanations

    instances of the word "see"

    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
    197
    +0.13
    0.7%
    478
    +0.12
    0.6%
    116
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.13
    0.03
    103
    +0.12
    0.03
    223
    +0.10
    0.02
    Negative Logits
    ¤
    -2.04
    ¸
    -1.80
    ½
    -1.75
    eners
    -1.65
    ime
    -1.58
    į
    -1.58
    ute
    -1.54
    ¬
    -1.52
    Ń
    -1.51
    den
    -1.50
    POSITIVE LOGITS
     cref
    2.22
    cknowled
    1.78
     recent
    1.52
    andum
    1.52
     above
    1.51
    ishes
    1.51
     embodiment
    1.50
     below
    1.50
     Chapter
    1.49
    mining
    1.46
    Activations Density 0.080%

    No Known Activations