© 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. 26594
    Prev
    Next
    INDEX
    Explanations

    references to programming parameters and their configuration in code

    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
    30
    +0.12
    0.7%
    42
    +0.11
    0.6%
    341
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.12
    0.06
    95
    +0.11
    0.05
    164
    +0.10
    0.05
    Negative Logits
    fony
    -1.52
    ?",
    -1.48
    gregation
    -1.48
    agem
    -1.47
    doibase
    -1.47
    inger
    -1.45
    eners
    -1.44
    croft
    -1.42
     behaviour
    -1.42
     ?"
    -1.42
    POSITIVE LOGITS
    suppl
    1.90
    ¦
    1.60
    »
    1.57
    GREEK
    1.55
     forth
    1.50
    ¯
    1.49
     unfolded
    1.48
     dawn
    1.47
     probabilities
    1.42
     align
    1.37
    Activations Density 0.044%

    No Known Activations