© 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 EvalsExportsAPI 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. 28512
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols often associated with text encoding errors

    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
    219
    +0.15
    0.8%
    380
    +0.14
    0.8%
    130
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.15
    0.01
    219
    +0.14
    0.01
    174
    +0.14
    0.01
    Negative Logits
    ¿½
    -3.40
    Ĺ
    -2.88
    ¬
    -2.85
    ī
    -2.81
    ³
    -2.81
    ħ
    -2.78
    ¼
    -2.75
    ¡
    -2.71
    »
    -2.71
    ¶
    -2.71
    POSITIVE LOGITS
    ferroni
    1.63
    culus
    1.56
    âĢij
    1.53
    aceae
    1.51
    furt
    1.48
    tech
    1.46
    lis
    1.46
    PHA
    1.45
    ligt
    1.44
    mile
    1.40
    Activations Density 0.006%

    No Known Activations