© 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. 30260
    Prev
    Next
    INDEX
    Explanations

    the concept of being overwhelmed

    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
    +0.22
    1.3%
    467
    +0.13
    0.7%
    139
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.22
    0.04
    53
    +0.13
    0.04
    56
    +0.12
    0.01
    Negative Logits
    Åij
    -1.52
    schen
    -1.48
    nj
    -1.45
    ORS
    -1.39
    +}
    -1.39
    zo
    -1.38
    aks
    -1.36
    zk
    -1.33
     Municip
    -1.33
    zen
    -1.31
    POSITIVE LOGITS
    µ
    2.26
    °
    1.99
    ¤
    1.78
    Īĺ
    1.78
    ª
    1.73
    ¥
    1.71
    ľĵ
    1.60
    £
    1.59
    estion
    1.56
    Ĥ¬
    1.53
    Activations Density 4.709%

    No Known Activations