© 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. 24877
    Prev
    Next
    INDEX
    Explanations

    file-related operation commands or functions

    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
    23
    +0.19
    1.1%
    353
    +0.16
    0.9%
    375
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.19
    0.02
    56
    +0.16
    0.03
    343
    +0.14
    0.03
    Negative Logits
    Ĵ
    -3.62
    ĨĴ
    -3.10
    IJ
    -2.92
    ↵↵
    -2.91
    ↵
    -2.91
    ↵
    -2.91
    ↵↵
    -2.91
                  ↵
    -2.91
    ↵↵
    -2.91
    -2.91
    POSITIVE LOGITS
     intimate
    1.49
    ^*\
    1.49
     ‘
    1.48
    ‘
    1.44
    [\
    1.43
     gentle
    1.42
     innocent
    1.41
     introduce
    1.40
    ()[
    1.40
     abusive
    1.39
    Activations Density 0.236%

    No Known Activations