© 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. 29706
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "that"

    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
    8
    +0.13
    0.7%
    444
    +0.13
    0.7%
    15
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.11
    209
    +0.13
    0.07
    402
    +0.13
    0.07
    Negative Logits
    ĻĤ
    -1.69
    ®
    -1.69
    seys
    -1.68
    eness
    -1.57
    ¥
    -1.54
    ties
    -1.54
    ·¸
    -1.51
    ·
    -1.47
    µ
    -1.46
    ials
    -1.45
    POSITIVE LOGITS
    <
    1.48
    {};
    1.44
     donc
    1.44
     thus
    1.40
    "/>
    1.39
    .";
    1.39
    *]{}.
    1.38
     likely
    1.38
     presumably
    1.38
    "</
    1.37
    Activations Density 1.570%

    No Known Activations