© 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. 25935
    Prev
    Next
    INDEX
    Explanations

    closing brackets and their attributes

    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
    56
    +0.14
    0.8%
    435
    +0.13
    0.7%
    354
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.14
    0.05
    354
    +0.13
    0.04
    295
    +0.13
    0.04
    Negative Logits
     minded
    -1.49
     parentheses
    -1.48
     process
    -1.48
     maxima
    -1.47
     exceptions
    -1.42
     rule
    -1.41
    áĢº
    -1.40
     ONE
    -1.33
     Wales
    -1.32
     freak
    -1.31
    POSITIVE LOGITS
    illard
    2.05
    ocur
    1.90
    assing
    1.68
    arty
    1.63
    oir
    1.62
    connected
    1.61
    ":{"
    1.60
    ault
    1.55
    osph
    1.55
    asic
    1.54
    Activations Density 0.192%

    No Known Activations