© 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. 23025
    Prev
    Next
    INDEX
    Explanations

    terms related to security and management systems

    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
    23
    +0.16
    0.9%
    200
    +0.13
    0.7%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.16
    0.10
    51
    +0.13
    0.10
    23
    +0.11
    0.05
    Negative Logits
    »¿
    -2.27
    IJ
    -2.26
    ¼
    -2.18
    č↵
    -2.14
    č↵
    -2.14
               ↵
    -2.14
    ↵↵
    -2.14
    ↵
    -2.14
    -2.14
    ↵↵
    -2.14
    POSITIVE LOGITS
     caution
    1.83
    osterone
    1.61
    ---|---
    1.48
     expected
    1.48
     applied
    1.45
    ---|---|---
    1.44
    cker
    1.42
     notation
    1.42
     threshold
    1.41
    idth
    1.39
    Activations Density 0.916%

    No Known Activations