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

    Neuronpedia

    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. 25664
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical references

    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
    131
    +0.12
    0.7%
    30
    +0.11
    0.6%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.12
    0.03
    221
    +0.11
    0.02
    56
    +0.11
    0.11
    Negative Logits
    Ī
    -2.45
    ĻĤ
    -2.45
    ģ
    -2.41
    ī
    -2.29
    Īĺ
    -2.28
    £
    -2.20
    ±
    -1.97
    ³
    -1.96
    ¦
    -1.93
    ¯
    -1.91
    POSITIVE LOGITS
    forth
    1.60
    ncia
    1.59
    tainment
    1.44
    otic
    1.36
    ÂĢÂĤ
    1.34
    ological
    1.33
    aceut
    1.32
    enz
    1.30
    BSD
    1.29
    agent
    1.29
    Activations Density 1.772%

    No Known Activations