© 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. 25888
    Prev
    Next
    INDEX
    Explanations

    instances of the word "might" indicating possibility or uncertainty

    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
    4
    +0.12
    0.6%
    187
    +0.11
    0.6%
    106
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    486
    +0.12
    0.06
    236
    +0.11
    0.04
    202
    +0.10
    0.04
    Negative Logits
    —"
    -1.66
    enne
    -1.60
    .—
    -1.57
    avelength
    -1.57
    —
    -1.51
    ilies
    -1.49
    —'
    -1.45
     Agency
    -1.45
    ome
    -1.44
     Gardens
    -1.43
    POSITIVE LOGITS
    ķ
    3.71
    ľ
    3.33
    Ħ
    3.22
    »
    3.21
    Ľ
    3.17
    ĸ´
    3.17
    ĻĤ
    3.17
    ģ
    3.16
    §
    3.14
    ¦
    3.13
    Activations Density 0.054%

    No Known Activations