© 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. 28205
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Be" to highlight existence or presence

    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
    +0.18
    1.1%
    369
    +0.18
    1.0%
    44
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.18
    0.04
    191
    +0.18
    0.03
    251
    +0.17
    0.03
    Negative Logits
    Ĥ
    -2.32
    ľ
    -2.18
    ij
    -1.92
    Ł
    -1.83
    ¦
    -1.82
    Ĺ
    -1.80
    Ħ
    -1.77
    Ĭ
    -1.75
    ŀ
    -1.75
    ¥
    -1.74
    POSITIVE LOGITS
    zier
    2.38
    ijing
    2.01
    haviour
    2.01
    aucoup
    1.89
    hav
    1.83
    rets
    1.64
    houses
    1.62
    reng
    1.60
    ît
    1.59
    uj
    1.55
    Activations Density 0.010%

    No Known Activations