© 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. 29707
    Prev
    Next
    INDEX
    Explanations

    code structure elements and program control statements

    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
    81
    +0.13
    0.7%
    114
    +0.12
    0.7%
    458
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.13
    0.13
    53
    +0.12
    0.11
    247
    +0.12
    0.10
    Negative Logits
     remotely
    -1.55
    ree
    -1.46
     Redistributions
    -1.45
    vez
    -1.43
    hors
    -1.42
    ity
    -1.40
     assignment
    -1.38
    uality
    -1.36
     corpus
    -1.33
     viruses
    -1.32
    POSITIVE LOGITS
    IJ
    1.75
    ª
    1.66
    hesis
    1.62
    ī
    1.59
    ful
    1.56
    ĸ´
    1.53
    aced
    1.47
    apore
    1.39
    eful
    1.39
     chair
    1.38
    Activations Density 0.121%

    No Known Activations