© 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 EvalsExportsinterp-engineNEWAPI 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. 23305
    Prev
    Next
    INDEX
    Explanations

    the logical operators 'or' indicating alternatives or options in a discussion

    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
    168
    +0.13
    0.7%
    117
    +0.13
    0.7%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.13
    0.06
    249
    +0.13
    0.05
    347
    +0.12
    0.04
    Negative Logits
     mine
    -1.57
     anesthetized
    -1.48
     awake
    -1.47
    midt
    -1.46
     .$$
    -1.44
    hee
    -1.41
    )}.$$
    -1.39
    lesh
    -1.38
    ence
    -1.38
    )}$$
    -1.38
    POSITIVE LOGITS
    ģ
    1.92
    »
    1.65
     -,
    1.50
    Ĥ
    1.50
    ĨĴ
    1.50
     contempor
    1.49
    £
    1.47
    ijan
    1.44
    ī
    1.43
    esses
    1.37
    Activations Density 0.148%

    No Known Activations