© 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. 27136
    Prev
    Next
    INDEX
    Explanations

    quotes and speech formatting

    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
    478
    +0.16
    0.9%
    40
    +0.14
    0.8%
    261
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.16
    0.03
    308
    +0.14
    0.01
    467
    +0.13
    0.02
    Negative Logits
     computed
    -1.65
     Wrote
    -1.56
    ophil
    -1.46
    oning
    -1.44
    onuclear
    -1.44
    imer
    -1.41
    ych
    -1.40
    "?
    -1.38
     designed
    -1.38
    rypt
    -1.36
    POSITIVE LOGITS
    Į
    2.32
    ¼
    2.21
    ½
    2.08
    ¦
    1.98
    ľ
    1.97
    İ
    1.84
    ¿½
    1.81
    ĥ½
    1.79
    ¤
    1.79
    ĻĤ
    1.77
    Activations Density 3.129%

    No Known Activations