© 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. 28408
    Prev
    Next
    INDEX
    Explanations

    phrases related to unlocking or accessing features

    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%
    156
    +0.13
    0.8%
    173
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.16
    0.01
    317
    +0.13
    0.01
    383
    +0.13
    0.01
    Negative Logits
    ======================
    -1.79
    elf
    -1.72
    anner
    -1.72
    ----------------------
    -1.70
    MSO
    -1.69
    ===========================
    -1.66
    ubert
    -1.63
    =======================
    -1.61
    ==================
    -1.59
    blogger
    -1.55
    POSITIVE LOGITS
     aisle
    1.92
    ptions
    1.89
    ing
    1.86
    ingly
    1.84
    indo
    1.68
     holes
    1.67
     gaps
    1.61
    holes
    1.61
    enance
    1.60
     disabilities
    1.59
    Activations Density 0.018%

    No Known Activations