© 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 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. 28340
    Prev
    Next
    INDEX
    Explanations

    references to training courses

    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
    1.1%
    376
    +0.13
    0.8%
    241
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.18
    0.01
    499
    +0.13
    0.01
    361
    +0.13
    0.01
    Negative Logits
    ĥ½
    -3.58
    §
    -3.19
    ¦
    -3.19
    ĻĤ
    -3.19
    ±
    -3.18
    Ń
    -3.14
    ¥
    -3.05
    ©
    -3.05
    İ
    -3.04
    Ħ
    -3.02
    POSITIVE LOGITS
    creen
    1.99
    pot
    1.84
    uit
    1.79
    umber
    1.65
    ong
    1.65
     (>
    1.64
    oon
    1.62
    etting
    1.59
    helf
    1.59
    eller
    1.58
    Activations Density 0.020%

    No Known Activations