© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    references to the significance or necessity of various concepts and actions

    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
    193
    +0.13
    0.7%
    288
    +0.12
    0.7%
    468
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.13
    0.04
    193
    +0.12
    0.02
    239
    +0.11
    0.03
    Negative Logits
    Ļª
    -4.66
    ĻĤ
    -4.33
    ĸ
    -4.24
    Īĺ
    -4.20
    ģ
    -4.17
    ↵
    -4.15
    ↵
    -4.15
    -4.15
    -4.15
    ↵
    -4.15
    POSITIVE LOGITS
    "}](#
    1.81
    held
    1.69
    included
    1.65
     enough
    1.54
    office
    1.54
    ifen
    1.49
    cgi
    1.48
     aired
    1.47
    /$
    1.47
    Springer
    1.47
    Activations Density 0.250%

    No Known Activations