© 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. 26602
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    +0.16
    0.9%
    317
    +0.13
    0.7%
    334
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.16
    0.02
    138
    +0.13
    0.02
    334
    +0.12
    0.02
    Negative Logits
    ĭ
    -2.23
    ´
    -1.98
    ij
    -1.94
    ·¸
    -1.91
    º
    -1.84
    ¿½
    -1.79
    Ī
    -1.78
    «
    -1.67
    ®
    -1.67
    ĺ
    -1.64
    POSITIVE LOGITS
    giving
    2.18
    emit
    1.57
    asio
    1.56
    iano
    1.56
    lı
    1.53
    xsl
    1.50
    gery
    1.49
    iei
    1.48
    oslav
    1.45
    izumab
    1.41
    Activations Density 4.230%

    No Known Activations