© 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. 25519
    Prev
    Next
    INDEX
    Explanations

    instances of the numerical code "126"

    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
    315
    +0.15
    0.8%
    288
    +0.12
    0.6%
    434
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.15
    0.02
    297
    +0.12
    0.01
    107
    +0.11
    0.01
    Negative Logits
    ctrine
    -1.46
     forth
    -1.43
    atur
    -1.41
    textstyle
    -1.39
     uniqueness
    -1.33
     distinction
    -1.32
    .*;
    -1.32
    apons
    -1.31
     differently
    -1.31
    ted
    -1.30
    POSITIVE LOGITS
    ī
    1.91
    ľ
    1.91
    ·
    1.71
    Ł
    1.69
    ¥
    1.67
    gel
    1.66
    ¶
    1.62
    ª
    1.57
    Ľ
    1.57
    ying
    1.55
    Activations Density 0.006%

    No Known Activations