© 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. 26461
    Prev
    Next
    INDEX
    Explanations

    phrases regarding exemptions or conditions related to regulations or licenses

    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
    283
    +0.14
    0.8%
    330
    +0.13
    0.7%
    269
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.14
    0.03
    462
    +0.13
    0.02
    330
    +0.12
    0.03
    Negative Logits
    esta
    -1.66
    %).
    -1.56
    $).
    -1.53
    '));
    -1.52
    '),
    -1.50
     lately
    -1.41
    '))
    -1.40
     since
    -1.36
    omb
    -1.36
    vo
    -1.36
    POSITIVE LOGITS
    Ļª
    2.35
    ©
    2.29
    ª
    2.26
    µ
    2.10
    IJ
    2.03
    ¿
    2.01
    ¨
    1.99
    ¦
    1.98
    ´
    1.98
    Ŀ
    1.84
    Activations Density 0.037%

    No Known Activations