© 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. 25674
    Prev
    Next
    INDEX
    Explanations

    references to utility functions or classes

    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
    376
    +0.18
    1.0%
    392
    +0.18
    1.0%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.18
    0.03
    379
    +0.18
    0.02
    301
    +0.13
    0.01
    Negative Logits
    ľĵ
    -4.06
    ĥ
    -3.44
    ¿½
    -3.25
    ľ
    -3.18
    ĵ
    -3.15
    §
    -3.06
    ı
    -3.03
    ħ
    -3.03
    ij
    -3.01
    ¬
    -2.90
    POSITIVE LOGITS
    bow
    1.53
    enstein
    1.50
    eval
    1.47
    ière
    1.46
    lay
    1.45
    opot
    1.43
    pread
    1.42
    astom
    1.42
    had
    1.42
    cript
    1.41
    Activations Density 0.020%

    No Known Activations