© 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. 28429
    Prev
    Next
    INDEX
    Explanations

    references to livestock, particularly cows and related terms like herds and calves

    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
    156
    +0.16
    1.0%
    71
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.16
    0.01
    77
    +0.12
    0.01
    184
    +0.12
    0.01
    Negative Logits
    ľ
    -3.51
    Ħ
    -3.32
    ·
    -3.16
    ı
    -3.16
    ĺ
    -3.15
    ĵ
    -3.04
    ³
    -2.98
    ¯
    -2.96
    Ķ
    -2.92
    ¦
    -2.90
    POSITIVE LOGITS
    ong
    1.83
    erie
    1.78
    yard
    1.63
    ards
    1.61
    esian
    1.60
    isecond
    1.59
    imeter
    1.58
    ”,
    1.57
    afe
    1.54
    park
    1.54
    Activations Density 0.016%

    No Known Activations