© 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. 25438
    Prev
    Next
    INDEX
    Explanations

    instances of timestamps or time-related information

    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
    481
    +0.13
    0.7%
    394
    +0.12
    0.7%
    165
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.13
    0.03
    499
    +0.12
    0.03
    305
    +0.10
    0.02
    Negative Logits
     ↵
    -2.83
    -2.83
    ↵
    -2.83
    ↵
    -2.83
    -2.83
    ↵
    -2.83
    -2.83
    ↵            ↵
    -2.83
    ↵
    -2.83
    -2.83
    POSITIVE LOGITS
    ť
    1.66
    stitution
    1.57
    Äį
    1.57
    ensions
    1.50
    PLIED
    1.44
    phis
    1.43
    burg
    1.43
     swallowing
    1.38
    uku
    1.37
    til
    1.36
    Activations Density 0.021%

    No Known Activations