© 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. 26358
    Prev
    Next
    INDEX
    Explanations

    terms related to accumulation and aggregation

    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
    +0.20
    1.1%
    156
    +0.18
    1.1%
    148
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.20
    0.01
    141
    +0.18
    0.01
    45
    +0.17
    0.01
    Negative Logits
    ounded
    -1.58
    ians
    -1.43
    olson
    -1.43
    cco
    -1.40
    ubicin
    -1.39
    *âĢIJ
    -1.38
    keit
    -1.38
    ridges
    -1.36
    CRO
    -1.35
    rained
    -1.33
    POSITIVE LOGITS
    ¤
    1.73
     truths
    1.57
     moments
    1.46
    enti
    1.46
    icit
    1.45
     behind
    1.45
     ages
    1.42
    ictions
    1.42
    ently
    1.41
    entially
    1.37
    Activations Density 0.009%

    No Known Activations