© 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. 24074
    Prev
    Next
    INDEX
    Explanations

    expressions of contemplation or cognitive processing

    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
    116
    +0.14
    0.8%
    138
    +0.12
    0.7%
    223
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.05
    223
    +0.12
    0.03
    222
    +0.12
    0.04
    Negative Logits
    tin
    -1.52
     feel
    -1.50
    tered
    -1.46
     hers
    -1.43
    stairs
    -1.39
     mood
    -1.39
    ivated
    -1.38
    feel
    -1.38
     mine
    -1.34
    rceil
    -1.33
    POSITIVE LOGITS
    ©
    3.32
    Ħ
    3.20
    ī
    3.13
    ŀ
    3.12
    ¼
    3.09
    ²
    3.06
    ¦
    3.02
    ħ
    3.01
    ij
    2.99
    Ń
    2.94
    Activations Density 0.451%

    No Known Activations