© 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. 25540
    Prev
    Next
    INDEX
    Explanations

    quantitative performance metrics, particularly related to points scored in games

    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
    376
    +0.14
    0.8%
    209
    +0.12
    0.7%
    286
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.14
    0.03
    66
    +0.12
    0.03
    286
    +0.11
    0.03
    Negative Logits
    ĥ½
    -3.59
    §
    -3.49
    ·
    -3.34
    ¥
    -3.14
    ¦
    -3.13
    Ľ
    -3.13
    ¿½
    -3.02
    ³
    -3.00
    ĥ
    -2.97
    Ĥ¬
    -2.95
    POSITIVE LOGITS
    heet
    2.36
    hips
    2.07
    heets
    2.06
     shooter
    1.98
    film
    1.88
    manship
    1.85
    ource
    1.84
    chip
    1.79
    creen
    1.78
    card
    1.75
    Activations Density 0.025%

    No Known Activations