© 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. 27066
    Prev
    Next
    INDEX
    Explanations

    the word "cannot"

    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
    100
    +0.14
    0.8%
    23
    +0.14
    0.8%
    202
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.14
    0.04
    372
    +0.14
    0.03
    415
    +0.13
    0.03
    Negative Logits
    Ŀ
    -2.54
    Ľ
    -2.33
    ¢
    -2.17
    »
    -2.17
    ģ
    -2.17
    Ĵ
    -2.16
    ³
    -2.06
    ĸ
    -2.05
    ľĵ
    -2.01
    §
    -1.97
    POSITIVE LOGITS
    otherwise
    1.56
    vas
    1.53
     empty
    1.49
     harm
    1.43
     miss
    1.43
     tam
    1.42
     hereto
    1.41
    hang
    1.41
    ám
    1.40
     Zar
    1.40
    Activations Density 0.014%

    No Known Activations