© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25903
    Prev
    Next
    INDEX
    Explanations

    references to null or undefined values in code 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
    163
    +0.15
    0.8%
    127
    +0.14
    0.8%
    11
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.15
    0.04
    163
    +0.14
    0.02
    127
    +0.14
    0.04
    Negative Logits
     manually
    -1.53
    nae
    -1.52
    )',
    -1.50
    "}](#
    -1.49
    )?
    -1.46
    UTC
    -1.46
     Iceland
    -1.45
    mine
    -1.41
    pps
    -1.39
     uninsured
    -1.38
    POSITIVE LOGITS
    ¤
    2.19
    ½
    1.81
    ĨĴ
    1.76
    ĸ´
    1.73
     emerged
    1.60
    century
    1.59
    ¿
    1.58
    ĸ
    1.54
    ocene
    1.50
     existence
    1.50
    Activations Density 0.320%

    No Known Activations