© 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. 30703
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    167
    +0.14
    0.8%
    54
    +0.11
    0.6%
    110
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.14
    0.47
    98
    +0.11
    0.21
    228
    +0.11
    0.32
    Negative Logits
    =%
    -1.62
    ionale
    -1.57
    erad
    -1.53
    =”
    -1.52
    ergic
    -1.50
    âĢĬ
    -1.43
    quier
    -1.41
    ifax
    -1.39
    bic
    -1.39
    onial
    -1.36
    POSITIVE LOGITS
    ŀ
    2.61
    Ń
    2.42
    §
    2.41
    «
    2.38
    ©
    2.31
    ¹
    2.27
    °
    2.24
    ĵ
    2.22
    Ļª
    2.16
    ĥ
    2.11
    Activations Density 2.880%

    No Known Activations