© 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. 26420
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax in programming languages

    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
    156
    +0.19
    1.1%
    323
    +0.14
    0.8%
    484
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.19
    0.05
    376
    +0.14
    0.06
    363
    +0.12
    0.06
    Negative Logits
     |
    -1.64
     \|
    -1.47
    googleapis
    -1.44
     License
    -1.43
    arching
    -1.37
    aligned
    -1.36
     Press
    -1.35
     between
    -1.32
    rapeutic
    -1.29
    rapeutics
    -1.28
    POSITIVE LOGITS
    odom
    1.73
    ors
    1.69
    pero
    1.65
    naire
    1.63
    ore
    1.55
    oque
    1.43
    &#
    1.41
     seriously
    1.39
    ption
    1.34
    iens
    1.33
    Activations Density 0.633%

    No Known Activations