© 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. 25716
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character "č" in the text

    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
    282
    +0.12
    0.7%
    264
    +0.12
    0.7%
    260
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.12
    0.16
    135
    +0.12
    0.13
    337
    +0.11
    0.12
    Negative Logits
    emic
    -1.75
    eding
    -1.46
    gin
    -1.45
    beth
    -1.42
    gtr
    -1.38
     Liberals
    -1.37
     tracks
    -1.35
    uro
    -1.35
    fty
    -1.29
     addict
    -1.27
    POSITIVE LOGITS
    º
    1.68
    ocation
    1.67
     flourish
    1.57
    ienne
    1.52
    ateness
    1.51
    eness
    1.50
    owski
    1.45
    msgstr
    1.43
     thereon
    1.42
     msgid
    1.41
    Activations Density 0.368%

    No Known Activations