© 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. 28892
    Prev
    Next
    INDEX
    Explanations

    linear concepts and terminology related to mathematical functions and structures

    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
    +0.20
    1.2%
    470
    +0.10
    0.6%
    472
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.20
    0.01
    353
    +0.10
    0.01
    57
    +0.10
    0.01
    Negative Logits
    rog
    -1.75
    rey
    -1.73
    ager
    -1.66
    rocy
    -1.63
    rov
    -1.53
    rac
    -1.50
    orporated
    -1.48
    rian
    -1.46
    orters
    -1.43
    agers
    -1.43
    POSITIVE LOGITS
    Ł
    2.47
    ¢
    2.33
    ĻĤ
    2.32
    ģ
    2.22
    ij
    2.16
    £
    2.15
    ŀ
    2.13
    Ī
    2.12
    °
    2.10
    Īĺ
    2.08
    Activations Density 0.224%

    No Known Activations