© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27014
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a follow-up action or assessment in medical or procedural contexts

    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
    222
    +0.12
    0.7%
    167
    +0.12
    0.7%
    229
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.12
    0.02
    167
    +0.12
    0.03
    218
    +0.12
    0.02
    Negative Logits
    ))$
    -1.64
    \}$,
    -1.61
    emb
    -1.58
    ))$,
    -1.58
    FIL
    -1.54
    \}$
    -1.52
    ))$.
    -1.48
    til
    -1.43
    alam
    -1.41
    ppat
    -1.37
    POSITIVE LOGITS
    Ń
    2.48
    ±
    2.28
    ij
    2.15
    ĩ
    2.13
    ı
    2.02
    ©
    1.96
    Ģ
    1.95
    ·
    1.91
    »
    1.88
    ¾
    1.85
    Activations Density 0.132%

    No Known Activations