© 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. 2-MLP-SM
    11. 23085
    Prev
    Next
    INDEX
    Explanations

    HTML opening tags

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.15
    0.8%
    307
    +0.15
    0.8%
    484
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.15
    0.02
    269
    +0.15
    0.02
    307
    +0.12
    0.02
    Negative Logits
    INGTON
    -1.65
    ject
    -1.52
    plications
    -1.39
    TRODUCTION
    -1.36
    quire
    -1.36
    blems
    -1.36
    duction
    -1.35
    inia
    -1.30
    Tc
    -1.30
     worms
    -1.29
    POSITIVE LOGITS
    ģ
    2.54
    Īĺ
    2.39
    ĥ
    2.39
    Ļª
    2.29
    ĻĤ
    2.20
    º
    2.14
    Ĩ
    2.13
    Ĥ
    2.02
    istic
    1.98
    Ĥ¬
    1.94
    Activations Density 0.499%

    No Known Activations