© 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. 26628
    Prev
    Next
    INDEX
    Explanations

    the word "keeps."

    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
    +0.18
    1.0%
    111
    +0.13
    0.7%
    1
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.18
    0.02
    50
    +0.13
    0.02
    111
    +0.11
    0.02
    Negative Logits
    eLife
    -1.83
    dings
    -1.75
    inux
    -1.73
    ttp
    -1.71
    hood
    -1.66
    culus
    -1.65
    cies
    -1.62
    chers
    -1.59
    ught
    -1.56
    s
    -1.54
    POSITIVE LOGITS
    ĻĤ
    2.44
    µ
    2.06
     track
    1.84
    ķ
    1.84
    Īĺ
    1.82
    ¶
    1.72
    ²
    1.72
    ļ
    1.70
    ¸
    1.70
    Ĥ¬
    1.66
    Activations Density 0.045%

    No Known Activations