© 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. 23144
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate reasoning or justification

    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
    319
    +0.11
    0.6%
    145
    +0.11
    0.6%
    371
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.11
    0.01
    242
    +0.11
    0.03
    318
    +0.11
    0.01
    Negative Logits
    £
    -2.69
    ľĵ
    -2.60
    IJ
    -2.55
    ł
    -2.46
    Ľ
    -2.44
    ľ
    -2.40
    ļ
    -2.38
    ¥
    -2.38
    Ĵ
    -2.31
     ↵
    -2.28
    POSITIVE LOGITS
    rely
    1.74
     your
    1.62
    ubert
    1.61
    ev
    1.57
     yourself
    1.55
    oud
    1.52
     tomorrow
    1.51
    ème
    1.51
    onas
    1.50
    _>
    1.46
    Activations Density 0.220%

    No Known Activations