© 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. 23755
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress and direction

    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
    150
    +0.12
    0.7%
    375
    +0.12
    0.7%
    179
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.12
    0.07
    407
    +0.12
    0.08
    123
    +0.11
    0.06
    Negative Logits
    cient
    -1.77
     generated
    -1.60
     moment
    -1.45
    hood
    -1.40
     capitalism
    -1.37
     guessing
    -1.33
     to
    -1.33
    \)
    -1.30
     perspective
    -1.30
    cing
    -1.29
    POSITIVE LOGITS
    »¿
    1.86
    ses
    1.74
     ↵
    1.56
    ↵↵
    1.56
    č↵
    1.56
    ↵↵↵
    1.56
    1.56
    ↵↵
    1.56
    ↵
    1.56
           ↵
    1.56
    Activations Density 0.705%

    No Known Activations