© 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. 28096
    Prev
    Next
    INDEX
    Explanations

    the verb "was" in various contexts

    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
    23
    +0.29
    1.7%
    478
    +0.15
    0.9%
    356
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.29
    0.14
    356
    +0.15
    0.11
    348
    +0.15
    0.09
    Negative Logits
    »¿
    -3.18
    ptions
    -2.30
    Ħ
    -2.29
    ģ
    -2.25
    Ī
    -2.19
    ł
    -2.08
    £
    -2.06
    ¢
    -2.04
    ·¸
    -2.02
    Ĥ
    -2.01
    POSITIVE LOGITS
     originally
    2.10
     unsuccessful
    2.08
     initially
    1.93
    hes
    1.91
    hers
    1.79
     discontinued
    1.78
     fortunate
    1.72
    her
    1.72
    raid
    1.68
     born
    1.66
    Activations Density 0.484%

    No Known Activations