© 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. MLP Post
    9. 0-MLP-SM
    11. 26321
    Prev
    Next
    INDEX
    Explanations

    the verb "sees" 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__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.24
    1.4%
    74
    +0.16
    0.9%
    115
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.24
    0.02
    74
    +0.16
    0.02
    54
    +0.14
    0.01
    Negative Logits
    ctin
    -1.68
    asone
    -1.62
    eurs
    -1.56
    ubert
    -1.56
    urities
    -1.51
    riber
    -1.49
    ="#
    -1.48
    MSO
    -1.45
    quart
    -1.44
    taire
    -1.43
    POSITIVE LOGITS
     fit
    1.59
     how
    1.56
     clear
    1.46
    awed
    1.45
     approximate
    1.45
    heric
    1.45
    ationally
    1.43
    al
    1.43
    ational
    1.41
    ations
    1.41
    Activations Density 0.020%

    No Known Activations