© 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. 26459
    Prev
    Next
    INDEX
    Explanations

    references to innovation and improvements 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
    156
    +0.31
    1.9%
    413
    +0.15
    0.9%
    365
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    413
    +0.31
    0.02
    156
    +0.15
    0.01
    95
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.69
    §
    -2.57
    »
    -2.40
    ½
    -2.32
    Ľ
    -2.26
    ·
    -2.16
    ¿
    -2.15
    ↵↵
    -2.08
    ↵Č
    -2.08
    č↵
    -2.08
    POSITIVE LOGITS
     centers
    1.64
    ulate
    1.60
     centres
    1.57
    ially
    1.53
     hypothesis
    1.51
    ually
    1.48
     measures
    1.45
     pertains
    1.44
    ctor
    1.43
     controls
    1.42
    Activations Density 0.020%

    No Known Activations