© 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. 28548
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly areas with the suffix "shire."

    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
    156
    +0.15
    0.9%
    503
    +0.12
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.15
    0.01
    503
    +0.12
    0.01
    71
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.18
    ĺ
    -1.85
    ij
    -1.81
    ľ
    -1.78
    ĵ
    -1.61
    İ
    -1.60
    ķ
    -1.54
    Ĵ
    -1.52
    ħ
    -1.48
    ±
    -1.47
    POSITIVE LOGITS
    à±ģ
    2.04
    àµį
    1.98
    vist
    1.86
    icum
    1.73
     herself
    1.72
    vre
    1.70
    à¯ģ
    1.70
    bane
    1.69
    bourne
    1.66
    àµ
    1.65
    Activations Density 0.007%

    No Known Activations