© 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. 26071
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "when"

    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
    47
    +0.15
    0.8%
    239
    +0.14
    0.8%
    332
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.11
    174
    +0.14
    0.08
    154
    +0.13
    0.09
    Negative Logits
    elijk
    -1.53
    ognitive
    -1.49
     facie
    -1.44
    adjoint
    -1.42
    ogical
    -1.42
     Interior
    -1.40
    oretical
    -1.38
    upid
    -1.36
    lying
    -1.35
    orems
    -1.30
    POSITIVE LOGITS
    Ģ
    2.22
    Į
    2.14
    Ĭ
    1.84
    ĥ
    1.82
    ±
    1.82
    Ħ
    1.82
    ¦
    1.66
    ħ
    1.64
    Ł
    1.58
     "/
    1.49
    Activations Density 1.667%

    No Known Activations