© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 29157
    Prev
    Next
    INDEX
    Explanations

    concepts related to autonomy and self-governance

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    156
    +0.17
    1.0%
    376
    +0.14
    0.8%
    29
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.17
    0.01
    29
    +0.14
    0.01
    79
    +0.13
    0.01
    Negative Logits
     celebrated
    -1.46
     Atlantic
    -1.43
     Wright
    -1.42
     coordinated
    -1.34
     Primer
    -1.33
     relentless
    -1.32
    yers
    -1.31
     Appellees
    -1.31
     gentle
    -1.31
    ritis
    -1.31
    POSITIVE LOGITS
    ¤
    2.79
    ±
    2.47
    ¸
    2.40
    ¼
    2.37
    ģ
    2.31
    Ĭ
    2.21
    ¹
    2.20
    ķ
    2.17
    ¦
    2.14
    Ł
    2.12
    Activations Density 0.013%

    No Known Activations