© 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. 30250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "failed."

    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
    +0.15
    0.8%
    72
    +0.13
    0.7%
    268
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.15
    0.03
    159
    +0.13
    0.03
    72
    +0.12
    0.03
    Negative Logits
     wasn
    -1.45
    aught
    -1.43
     shud
    -1.33
    woke
    -1.33
    raf
    -1.33
    ounded
    -1.32
     backed
    -1.32
    ---|---|---
    -1.31
    OULD
    -1.30
    ainen
    -1.28
    POSITIVE LOGITS
    Īĺ
    2.74
    ĻĤ
    2.44
    Ĥ¬
    2.42
    ²
    2.25
    ¨
    2.13
    Ľ
    2.03
    ¦
    2.02
    ľĵ
    2.00
    ª
    2.00
    ¹
    1.99
    Activations Density 0.014%

    No Known Activations