© 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. 28570
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Struct."

    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
    156
    +0.14
    0.8%
    376
    +0.12
    0.7%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.14
    0.01
    40
    +0.12
    0.01
    392
    +0.11
    0.01
    Negative Logits
    ¿
    -2.16
    ĥ½
    -2.15
    ³
    -1.92
     your
    -1.81
     prompt
    -1.80
     yourself
    -1.76
    ĵ
    -1.68
    ¬
    -1.67
    ¸
    -1.64
    Ĥ
    -1.64
    POSITIVE LOGITS
    idor
    1.80
    ural
    1.80
    ured
    1.79
    enstein
    1.75
    \]](
    1.65
    urally
    1.62
    istry
    1.61
    iom
    1.57
    ensible
    1.56
    imen
    1.55
    Activations Density 0.014%

    No Known Activations