© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26490
    Prev
    Next
    INDEX
    Explanations

    topics related to scientific research and technology

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.38
    2.3%
    156
    +0.15
    0.9%
    478
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.38
    0.10
    364
    +0.15
    0.08
    511
    +0.13
    0.04
    Negative Logits
     etc
    -2.08
    ”,
    -2.04
    zent
    -1.87
    etc
    -1.78
    ista
    -1.78
    ké
    -1.76
    ”.
    -1.76
     (“
    -1.73
    ibil
    -1.69
    oire
    -1.68
    POSITIVE LOGITS
    Ĥ
    1.94
    Ĺ
    1.92
    ľ
    1.69
    ±
    1.69
     thickening
    1.68
     refugees
    1.67
    »¿
    1.67
     stranger
    1.63
     mild
    1.61
     unsafe
    1.57
    Activations Density 1.927%

    No Known Activations