© 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. 30762
    Prev
    Next
    INDEX
    Explanations

    occurrences of "CP," likely indicating a focus on a specific term or concept related to legal or technical contexts

    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
    502
    +0.16
    0.9%
    369
    +0.15
    0.9%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.16
    0.01
    123
    +0.15
    0.01
    92
    +0.12
    0.01
    Negative Logits
    ĥ½
    -4.01
    Ĥ
    -3.50
    Ļª
    -3.38
    Ń
    -3.35
    »¿
    -3.29
    ľĵ
    -3.26
    ĭ
    -3.21
    ¸
    -3.21
    §
    -3.13
    ¾
    -3.11
    POSITIVE LOGITS
    film
    1.69
    kat
    1.69
    opa
    1.66
    krit
    1.63
    ulent
    1.60
    lei
    1.57
    bench
    1.53
    pute
    1.53
    ilee
    1.50
    ist
    1.49
    Activations Density 0.009%

    No Known Activations