© 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. 23150
    Prev
    Next
    INDEX
    Explanations

    opening parentheses

    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
    489
    +0.15
    0.8%
    364
    +0.10
    0.5%
    16
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.15
    0.04
    112
    +0.10
    0.04
    268
    +0.10
    0.04
    Negative Logits
    ,&
    -1.90
    izoph
    -1.61
    iler
    -1.59
    ón
    -1.58
    blogger
    -1.51
    urope
    -1.51
    ender
    -1.48
    onica
    -1.48
    obl
    -1.48
    onel
    -1.45
    POSITIVE LOGITS
    ĩ
    2.53
    »
    2.37
    ³
    2.30
    ij
    2.17
    ¯
    2.17
    Ĺ
    2.17
    į
    2.12
    ĭ
    2.08
    ħ
    2.04
    ²
    2.03
    Activations Density 0.121%

    No Known Activations