© 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. 29939
    Prev
    Next
    INDEX
    Explanations

    references to replacement or placement concepts 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
    376
    +0.17
    1.0%
    156
    +0.17
    1.0%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.17
    0.01
    249
    +0.17
    0.01
    392
    +0.11
    0.01
    Negative Logits
    ĥ½
    -3.40
    »¿
    -3.22
    Ĵ
    -3.13
    ¿
    -2.99
    Ī
    -2.97
    §
    -2.90
    Ĥ¬
    -2.87
    ²
    -2.86
    ķ
    -2.77
    ĩ
    -2.73
    POSITIVE LOGITS
    ary
    2.13
    ista
    1.97
    aria
    1.95
    gap
    1.94
    nel
    1.86
    ist
    1.84
    arily
    1.74
    icular
    1.72
    "}](#
    1.59
    ('',
    1.58
    Activations Density 0.031%

    No Known Activations