© 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. 26536
    Prev
    Next
    INDEX
    Explanations

    terms related to global phenomena or issues

    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
    1.2%
    376
    +0.14
    0.8%
    119
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.22
    0.01
    122
    +0.14
    0.01
    404
    +0.12
    0.01
    Negative Logits
    İ
    -2.05
    ĥ½
    -1.71
    ĨĴ
    -1.68
    ¬
    -1.58
    ı
    -1.46
    ables
    -1.46
    atement
    -1.43
    fully
    -1.43
    hler
    -1.40
    IJ
    -1.39
    POSITIVE LOGITS
    iss
    1.55
    "}](#
    1.50
     positioning
    1.39
    elles
    1.39
     minded
    1.34
    izza
    1.30
    esse
    1.30
     speaking
    1.28
    ella
    1.24
     impulse
    1.24
    Activations Density 0.009%

    No Known Activations