© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 23123
    Prev
    Next
    INDEX
    Explanations

    expressions indicating the presence of animals, particularly cats

    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
    376
    +0.11
    0.6%
    457
    +0.11
    0.6%
    256
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.11
    0.13
    182
    +0.11
    0.12
    505
    +0.10
    0.09
    Negative Logits
    ³
    -2.11
    Ļª
    -1.92
    Ĺ
    -1.85
     light
    -1.66
    »¿
    -1.66
    inner
    -1.60
     sudden
    -1.54
     notice
    -1.51
     hats
    -1.51
    ¿
    -1.50
    POSITIVE LOGITS
    esan
    2.12
    ului
    2.04
    xico
    1.79
    eca
    1.71
    ograf
    1.66
    uese
    1.66
    etica
    1.64
    ugu
    1.63
    \]](
    1.57
    ÃŃf
    1.56
    Activations Density 1.343%

    No Known Activations