© 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. 29582
    Prev
    Next
    INDEX
    Explanations

    statements asserting identity or existence

    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
    475
    +0.13
    0.7%
    187
    +0.11
    0.6%
    148
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.13
    0.24
    17
    +0.11
    0.16
    233
    +0.10
    0.17
    Negative Logits
     scint
    -1.82
     summary
    -1.38
     fiduc
    -1.36
     fatal
    -1.36
     nod
    -1.34
     union
    -1.32
     standards
    -1.32
    "}](#
    -1.32
    esy
    -1.28
     counts
    -1.27
    POSITIVE LOGITS
    ¤
    2.29
    ¬
    2.18
    ¿½
    2.13
    ®
    2.11
    ·
    2.07
    ľĵ
    2.04
    Ļª
    2.00
    º
    1.99
    Ń
    1.98
    ¨
    1.96
    Activations Density 0.691%

    No Known Activations