© 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. 26320
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating actions or intentions

    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
    396
    +0.12
    0.7%
    12
    +0.11
    0.6%
    365
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.38
    151
    +0.11
    0.31
    434
    +0.10
    0.30
    Negative Logits
    etine
    -1.74
     ownership
    -1.56
     hoping
    -1.54
     nv
    -1.49
    wagen
    -1.48
     if
    -1.44
     booked
    -1.44
    ered
    -1.43
     jeans
    -1.38
     anytime
    -1.36
    POSITIVE LOGITS
    Ĺ
    2.72
    ĵ
    2.17
    Ħ
    2.14
    Ŀ
    2.10
    º
    2.10
    ł
    2.10
    Ĵ
    2.06
    ļ
    2.01
    ¸
    1.91
    İ
    1.90
    Activations Density 1.644%

    No Known Activations