© 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. 25866
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or need

    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
    +0.23
    1.3%
    252
    +0.12
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.23
    0.02
    73
    +0.12
    0.01
    231
    +0.11
    0.01
    Negative Logits
    sburg
    -1.56
    PROM
    -1.54
    ahan
    -1.49
    errals
    -1.42
     Salem
    -1.41
    ahi
    -1.40
    unction
    -1.39
    OY
    -1.38
    anos
    -1.37
    urations
    -1.36
    POSITIVE LOGITS
    ½
    2.88
    Ĩ
    2.86
    ²
    2.82
    ł
    2.69
    ¢
    2.62
    ĩ
    2.60
    ¼
    2.59
    Ħ
    2.56
    °
    2.56
    ĥ
    2.56
    Activations Density 0.069%

    No Known Activations