© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    the preposition "of" used 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
    12
    +0.15
    0.9%
    478
    +0.15
    0.8%
    23
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.15
    0.02
    69
    +0.15
    0.02
    418
    +0.10
    -0.00
    Negative Logits
    ા
    -1.57
     pic
    -1.43
     reductase
    -1.43
     pumps
    -1.41
    het
    -1.41
    ERY
    -1.39
     levels
    -1.39
     platform
    -1.39
     cylinders
    -1.37
     pools
    -1.37
    POSITIVE LOGITS
    ĥ½
    2.23
    rivers
    1.65
    fluence
    1.62
    »¿
    1.60
    requency
    1.56
    :&
    1.47
     Facts
    1.45
    iasis
    1.41
    omorphisms
    1.40
    advant
    1.37
    Activations Density 0.063%

    No Known Activations