© 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. 30692
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "box."

    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
    115
    +0.13
    0.7%
    376
    +0.10
    0.6%
    172
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.13
    0.02
    275
    +0.10
    0.02
    172
    +0.09
    0.02
    Negative Logits
     yours
    -2.21
     say
    -1.87
    ...?"
    -1.78
     suppose
    -1.76
     APPEALS
    -1.69
    usement
    -1.64
     ?"
    -1.63
    '?"
    -1.60
     hers
    -1.59
     vain
    -1.57
    POSITIVE LOGITS
    plots
    2.58
    ing
    2.01
    ed
    1.97
    stro
    1.89
    work
    1.89
    nets
    1.79
    esan
    1.75
    pieces
    1.75
    ström
    1.74
    emos
    1.73
    Activations Density 0.063%

    No Known Activations