© 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. 23249
    Prev
    Next
    INDEX
    Explanations

    phrases related to future actions and expectations

    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
    +0.28
    1.6%
    223
    +0.14
    0.8%
    504
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.28
    0.03
    351
    +0.14
    0.04
    347
    +0.11
    0.04
    Negative Logits
    ipl
    -1.69
    django
    -1.60
    aland
    -1.48
    irez
    -1.43
     luck
    -1.40
    ILITY
    -1.40
    ür
    -1.38
    defer
    -1.36
    option
    -1.35
    iscopal
    -1.35
    POSITIVE LOGITS
     suggesting
    1.76
     figures
    1.67
    ij
    1.66
     unpublished
    1.56
     estimates
    1.54
     indicating
    1.52
    mere
    1.50
    wise
    1.49
     representing
    1.46
     mentions
    1.39
    Activations Density 1.631%

    No Known Activations