© 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. 28123
    Prev
    Next
    INDEX
    Explanations

    occurrences of the code or acronym "SK" in the text

    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
    285
    +0.12
    0.7%
    444
    +0.11
    0.6%
    391
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.12
    0.01
    285
    +0.11
    0.01
    309
    +0.10
    0.01
    Negative Logits
    «
    -2.09
    ľĵ
    -1.96
    ¿½
    -1.76
    Īĺ
    -1.75
    cluded
    -1.73
    ĥ½
    -1.68
    ¬
    -1.67
    ĭ
    -1.65
    Ĺ
    -1.64
    Ļª
    -1.60
    POSITIVE LOGITS
    ép
    1.77
    ibase
    1.67
    Foundation
    1.53
    ató
    1.51
    NUM
    1.47
    ERC
    1.45
    ings
    1.45
     advantage
    1.43
    pel
    1.43
    agem
    1.43
    Activations Density 0.121%

    No Known Activations