© 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. 25403
    Prev
    Next
    INDEX
    Explanations

    indicators of inquiries or questions about interest or qualification

    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
    +0.22
    1.2%
    210
    +0.12
    0.6%
    337
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.22
    -0.01
    188
    +0.12
    0.01
    174
    +0.11
    0.08
    Negative Logits
    riber
    -1.70
    ductive
    -1.67
     elif
    -1.64
    ento
    -1.58
    emplo
    -1.56
     luck
    -1.50
    stract
    -1.49
     migrated
    -1.47
    úblic
    -1.46
    translated
    -1.44
    POSITIVE LOGITS
    Ħ
    2.18
    ¹
    2.15
    ³
    2.08
    °
    1.92
    ī
    1.92
    Ģ
    1.89
    ļ
    1.89
    ģ
    1.88
    ĻĤ
    1.87
    ±
    1.83
    Activations Density 2.952%

    No Known Activations