© 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. 27934
    Prev
    Next
    INDEX
    Explanations

    expressions and references to humor and comedic elements

    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
    +0.18
    1.0%
    228
    +0.14
    0.8%
    77
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.18
    0.01
    347
    +0.14
    0.01
    77
    +0.12
    0.01
    Negative Logits
    ij
    -2.05
    ĵ
    -1.88
    usterity
    -1.82
    §
    -1.82
    ĥ
    -1.77
    ķ
    -1.72
    Ŀ
    -1.70
    ©
    -1.68
    Docket
    -1.68
    ı
    -1.68
    POSITIVE LOGITS
    istry
    2.19
    ious
    2.05
    ist
    1.97
    ously
    1.97
    cule
    1.84
    iously
    1.76
    pora
    1.75
    isms
    1.72
    etheless
    1.71
    lessness
    1.68
    Activations Density 0.020%

    No Known Activations