© 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. 29360
    Prev
    Next
    INDEX
    Explanations

    references to a curriculum vitae (CV) or related documentation

    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
    369
    +0.12
    0.7%
    221
    +0.12
    0.7%
    471
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.12
    0.01
    221
    +0.12
    0.01
    471
    +0.11
    0.01
    Negative Logits
    ĸ´
    -2.62
    ·¸
    -2.49
    Ļª
    -2.40
    ĥ½
    -2.40
    Ļ
    -2.30
    ĥ
    -2.28
    Ī
    -2.23
    ľ
    -2.22
    ¼
    -2.21
    ĭ
    -2.19
    POSITIVE LOGITS
    ariate
    1.90
    ulence
    1.90
    uple
    1.78
    ioni
    1.70
    ariant
    1.65
    ulent
    1.64
    ignon
    1.59
    oir
    1.55
    art
    1.53
    irus
    1.51
    Activations Density 0.006%

    No Known Activations