© 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. 29817
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing significance or importance

    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
    +0.18
    1.0%
    376
    +0.18
    1.0%
    237
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.18
    0.06
    110
    +0.18
    0.04
    72
    +0.15
    0.04
    Negative Logits
     varying
    -1.48
     caso
    -1.45
     based
    -1.44
     accordingly
    -1.43
    amphetamine
    -1.39
    derer
    -1.33
    }}$-
    -1.33
    $-
    -1.32
    called
    -1.32
    agn
    -1.29
    POSITIVE LOGITS
    Īĺ
    2.04
    ¢
    1.99
    ĻĤ
    1.67
    ľĵ
    1.63
    ités
    1.60
    stro
    1.57
    ł
    1.54
     relationships
    1.54
    º
    1.49
    Ļ
    1.49
    Activations Density 0.678%

    No Known Activations