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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25033
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence of an online or digital utility

    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
    +0.31
    1.8%
    111
    +0.16
    0.9%
    163
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.31
    0.03
    163
    +0.16
    0.01
    210
    +0.14
    -0.03
    Negative Logits
    <|outofrange|>
    -2.11
    ↵
    -2.11
    ↵↵
    -2.11
    č↵
    -2.11
    ↵
    -2.11
    ↵
    -2.11
     ↵
    -2.11
    ↵
    -2.11
    -2.11
    <|outofrange|>
    -2.11
    POSITIVE LOGITS
    <
    1.61
    :</
    1.60
     colleagues
    1.49
    .<
    1.49
    }</
    1.48
    roup
    1.42
    )</
    1.39
    %-
    1.39
    ======
    1.38
    Acknowled
    1.37
    Activations Density 2.816%

    No Known Activations