© 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. 25363
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Pop" 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
    48
    +0.14
    0.8%
    285
    +0.13
    0.8%
    437
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.14
    0.02
    437
    +0.13
    0.01
    452
    +0.10
    0.01
    Negative Logits
     slightest
    -1.66
     want
    -1.64
    )](#
    -1.63
     cross
    -1.60
    "?"
    -1.58
    ights
    -1.57
     lack
    -1.53
     certain
    -1.49
     miss
    -1.49
     wish
    -1.47
    POSITIVE LOGITS
    ulator
    1.93
    ulations
    1.84
    ULAR
    1.82
    agmatic
    1.81
    ulates
    1.80
    ulating
    1.80
    aggio
    1.78
    idable
    1.75
    ulous
    1.67
    forge
    1.64
    Activations Density 1.024%

    No Known Activations