© 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. 30365
    Prev
    Next
    INDEX
    Explanations

    phrases related to publication references or citations

    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
    502
    +0.14
    0.8%
    510
    +0.13
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.06
    438
    +0.13
    0.05
    373
    +0.11
    0.04
    Negative Logits
    Ĥ
    -2.74
    Ķ
    -2.67
    °
    -2.63
    ·¸
    -2.63
    ª
    -2.63
    ©
    -2.53
    ¿
    -2.51
    ķ
    -2.48
    ĥ
    -2.46
    ·
    -2.43
    POSITIVE LOGITS
    bian
    1.63
    recht
    1.57
    ino
    1.53
     lane
    1.53
     himself
    1.49
    ios
    1.47
    inho
    1.46
     flashes
    1.43
     matches
    1.43
    doped
    1.43
    Activations Density 4.678%

    No Known Activations