© 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. 26531
    Prev
    Next
    INDEX
    Explanations

    the word "ire."

    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
    376
    +0.13
    0.8%
    380
    +0.11
    0.6%
    125
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.13
    0.02
    133
    +0.11
    0.02
    31
    +0.10
    0.02
    Negative Logits
    '?"
    -1.73
     overex
    -1.49
     sudden
    -1.45
     sandy
    -1.44
     better
    -1.41
     Nass
    -1.36
     seaw
    -1.36
     disturbed
    -1.35
     muddy
    -1.33
     disturbance
    -1.32
    POSITIVE LOGITS
    ģ
    2.52
    Ģ
    2.38
    ½
    2.26
    ŀ
    2.23
    eur
    2.15
    ®
    2.15
    ¢
    2.04
    Ĭ
    2.03
    ĻĤ
    2.03
    esan
    1.99
    Activations Density 0.015%

    No Known Activations