© 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. 0-MLP-SM
    11. 29071
    Prev
    Next
    INDEX
    Explanations

    the word "respective" and related phrases that refer to distinct or particular entities or groups

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.19
    1.1%
    125
    +0.15
    0.9%
    121
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.19
    0.01
    121
    +0.15
    0.01
    257
    +0.13
    0.01
    Negative Logits
    clus
    -1.55
    anese
    -1.55
    enthal
    -1.52
    ÂĹ
    -1.51
     itself
    -1.51
    enson
    -1.50
    belt
    -1.41
    +"
    -1.38
     Symphony
    -1.36
    heimer
    -1.35
    POSITIVE LOGITS
     sexes
    1.67
    teen
    1.67
    idades
    1.51
    ities
    1.51
    ocial
    1.49
     exist
    1.49
    ials
    1.46
     generations
    1.43
    liament
    1.42
    iliar
    1.41
    Activations Density 0.009%

    No Known Activations