© 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. 29379
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "pencil" in various contexts

    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
    429
    +0.11
    0.6%
    489
    +0.10
    0.6%
    441
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.11
    0.01
    112
    +0.10
    0.01
    13
    +0.10
    0.01
    Negative Logits
    ĥ
    -2.70
    Īĺ
    -2.58
    Ĥ¬
    -2.54
    ĵ
    -2.35
    Ĥ
    -2.27
    Ħ
    -2.25
    ¿½
    -2.24
    ľ
    -2.21
    Ĺ
    -2.19
    ´
    -2.19
    POSITIVE LOGITS
    heets
    2.20
    heet
    2.12
    pace
    2.04
    ource
    1.95
    borough
    1.89
    burg
    1.86
    pot
    1.85
    ibrary
    1.81
    forge
    1.81
    borg
    1.79
    Activations Density 0.014%

    No Known Activations