© 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. 25738
    Prev
    Next
    INDEX
    Explanations

    the word "Things"

    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
    +0.13
    0.7%
    392
    +0.10
    0.6%
    285
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.13
    0.01
    365
    +0.10
    0.01
    77
    +0.10
    0.01
    Negative Logits
     myself
    -2.03
    ĥ½
    -1.95
    )?
    -1.74
    apine
    -1.72
    "?
    -1.71
    ESULT
    -1.66
    ).$
    -1.60
    '?
    -1.54
    \)
    -1.53
    pling
    -1.52
    POSITIVE LOGITS
    bridge
    1.61
    draft
    1.60
    ű
    1.59
     Bundes
    1.58
    arus
    1.53
     refe
    1.50
    Euro
    1.47
    endor
    1.47
     trouble
    1.46
    iedad
    1.46
    Activations Density 0.020%

    No Known Activations