© 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. 30464
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "state" in various contexts

    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
    91
    +0.13
    0.8%
    503
    +0.12
    0.7%
    213
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.13
    0.06
    91
    +0.12
    0.05
    336
    +0.12
    0.06
    Negative Logits
    ij
    -3.64
    İ
    -3.44
    ĭ
    -3.36
    ±
    -3.27
    º
    -3.19
    č↵
    -3.19
    ↵
    -3.19
    ↵
    -3.19
    ↵↵
    -3.19
    -3.19
    POSITIVE LOGITS
     favorites
    1.96
    oft
    1.87
    houses
    1.87
    etting
    1.80
    cript
    1.77
     aids
    1.76
    birds
    1.72
    craft
    1.72
    eed
    1.64
    keeping
    1.64
    Activations Density 0.357%

    No Known Activations