© 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. 29911
    Prev
    Next
    INDEX
    Explanations

    references to calendars or scheduling

    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
    385
    +0.13
    0.8%
    370
    +0.12
    0.7%
    301
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.13
    0.01
    370
    +0.12
    0.00
    48
    +0.10
    0.00
    Negative Logits
    ĥ½
    -2.07
    ¬
    -1.99
    ¯
    -1.93
    ¿½
    -1.82
    ´
    -1.77
    Ĥ¬
    -1.76
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.76
     different
    -1.75
    -1.71
    -1.71
    POSITIVE LOGITS
    ière
    2.06
    zilla
    1.82
    ville
    1.80
    mare
    1.77
    amble
    1.77
    cule
    1.76
    etable
    1.74
    nikov
    1.73
    etto
    1.71
    boat
    1.68
    Activations Density 0.010%

    No Known Activations