© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25033
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and end sentences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    122
    +0.16
    0.9%
    39
    +0.13
    0.7%
    147
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.16
    0.55
    56
    +0.13
    0.18
    203
    +0.13
    0.38
    Negative Logits
    Ĥ¬
    -2.31
    µ
    -2.30
    ŀ
    -2.25
    ·¸
    -2.09
    ↵↵
    -2.08
    ↵↵
    -2.08
    ↵↵
    -2.08
    -2.08
     ↵
    -2.08
    ↵
    -2.08
    POSITIVE LOGITS
     exactly
    1.69
    emis
    1.61
    Ex
    1.47
    dess
    1.45
     Appeals
    1.45
    aus
    1.44
    equ
    1.43
    Einstein
    1.41
     identical
    1.34
    :)
    1.33
    Activations Density 3.602%

    No Known Activations