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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26612
    Prev
    Next
    INDEX
    Explanations

    references to usefulness or practicality in various 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
    144
    +0.13
    0.7%
    248
    +0.11
    0.6%
    44
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.13
    0.04
    277
    +0.11
    0.04
    225
    +0.10
    0.04
    Negative Logits
    IJ
    -3.93
    ĻĤ
    -3.65
    Ļª
    -3.49
    ĸ
    -3.42
    ĨĴ
    -3.40
    ¯
    -3.37
    ¬
    -3.35
    į
    -3.28
    ģ
    -3.26
    §
    -3.18
    POSITIVE LOGITS
    \",
    1.85
    \"
    1.53
    ÃŃf
    1.50
    ===========================
    1.50
     prescriptions
    1.47
    doll
    1.44
     dos
    1.41
    ==================================
    1.40
    pora
    1.39
    ==========================
    1.36
    Activations Density 0.392%

    No Known Activations