© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28333
    Prev
    Next
    INDEX
    Explanations

    references to a "retiree" or individuals in retirement 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
    203
    +0.13
    0.7%
    388
    +0.13
    0.7%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.13
    0.02
    197
    +0.13
    0.01
    85
    +0.13
    0.01
    Negative Logits
    hler
    -1.67
    ities
    -1.63
    ffect
    -1.55
    afers
    -1.49
    izumab
    -1.49
    )">
    -1.43
    '?"
    -1.42
    ashing
    -1.41
     ich
    -1.40
    illance
    -1.37
    POSITIVE LOGITS
    rieve
    1.78
     affiliations
    1.61
    riev
    1.58
    journals
    1.49
    itals
    1.42
    pective
    1.41
    rieved
    1.39
    ained
    1.39
    stown
    1.36
    ford
    1.35
    Activations Density 0.015%

    No Known Activations