© 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 EvalsExportsAPI 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. 29080
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "PAT" or variations thereof

    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
    285
    +0.16
    0.9%
    369
    +0.16
    0.9%
    334
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.16
    0.01
    334
    +0.16
    0.01
    185
    +0.14
    0.01
    Negative Logits
    "?"
    -1.98
     why
    -1.64
    .""
    -1.64
    ating
    -1.58
    ...'
    -1.55
    "."
    -1.52
     ago
    -1.51
    cluding
    -1.51
    expand
    -1.46
    '?"
    -1.42
    POSITIVE LOGITS
    iens
    1.85
    IENT
    1.74
    IER
    1.71
    TERN
    1.68
    seud
    1.67
    etto
    1.66
    rice
    1.64
    LINE
    1.63
    rive
    1.59
    ULAR
    1.58
    Activations Density 0.093%

    No Known Activations